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

    Neuronpedia

    INDEX
    Explanations

    questions about degrees or levels of comparison

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

    no matter how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lapsingToolbar
    -0.38
     برانيه
    -0.36
    цездатний
    -0.35
    ↹
    -0.35
     nahilalakip
    -0.32
    IBarButtonItem
    -0.32
    Autoritní
    -0.32
    JNIEnv
    -0.31
    transQ
    -0.31
    Билгалдахарш
    -0.30
    POSITIVE LOGITS
    osoever
    0.54
    +#+#
    0.54
    rofoam
    0.52
    誰が
    0.52
     dubbio
    0.51
    CodedInputStream
    0.50
     Snowy
    0.50
    tration
    0.49
    wargs
    0.49
    posedge
    0.49
    Act Density 0.007%

    No Known Activations