Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    data analysis terms and statistical methods related to measurements and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Lists or vectors of IDs or names

    np_acts-logits-general · gemini-2.0-flash

    mathematical, statistical, and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.91
    endpush
    -0.80
     Normdatei
    -0.79
     يتيمه
    -0.78
     myſelf
    -0.76
     _('
    -0.76
    ſelves
    -0.74
     /\.(
    -0.73
     gynhyrchwyd
    -0.71
     ſame
    -0.71
    POSITIVE LOGITS
     format
    0.55
    gebob
    0.49
     propOrder
    0.49
    xymatrix
    0.45
    олові
    0.44
    IZED
    0.44
     olarak
    0.43
    롭
    0.43
     (
    0.42
    endaftaran
    0.42
    Act Density 1.538%

    No Known Activations