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

    Neuronpedia

    INDEX
    Explanations

    ellipses or omissions in text that indicate a continuation of thought or speech

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

    links to external resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gelöst
    -0.34
     Verhältnisse
    -0.32
    ospels
    -0.29
     infancia
    -0.29
     properly
    -0.28
     rescate
    -0.28
     Unterkunft
    -0.27
     Verhält
    -0.27
     should
    -0.27
     rueda
    -0.27
    POSITIVE LOGITS
    GOTREF
    0.76
     surla
    0.71
     resourceCulture
    0.67
     ProtoMessage
    0.65
     transfieras
    0.65
     հղումներ
    0.63
     invokingState
    0.60
    WebVitals
    0.59
     الحره
    0.58
    Hentet
    0.58
    Act Density 0.018%

    No Known Activations