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

    Neuronpedia

    INDEX
    Explanations

    concepts related to statistical modeling and data analysis methodologies

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

    latent models, encoding capability, digit recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.51
     autorytatywna
    -0.49
    InjectAttribute
    -0.44
    цездатний
    -0.44
     defStyleAttr
    -0.41
     podamos
    -0.40
    asants
    -0.40
    knapp
    -0.40
    anthemum
    -0.39
    ftagPool
    -0.39
    POSITIVE LOGITS
    \{\\
    0.47
    #
    0.42
     lodge
    0.41
     figure
    0.40
     Mald
    0.38
     abduction
    0.37
     lob
    0.36
     Smal
    0.36
     sumpay
    0.36
    obach
    0.36
    Act Density 0.361%

    No Known Activations