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

    Neuronpedia

    INDEX
    Explanations

    certain personal identifiers or qualifiers in the text

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

    Russian adjective endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iprot
    -0.57
     aikaa
    -0.53
    CWE
    -0.51
    ⓧ
    -0.48
    ValueStyle
    -0.48
    iettivo
    -0.47
    évaluateur
    -0.47
    不说
    -0.46
     Tiefe
    -0.46
     freio
    -0.45
    POSITIVE LOGITS
    ным
    0.94
    тным
    0.73
    льным
    0.72
    жным
    0.72
    ственным
    0.69
    тельным
    0.69
    чным
    0.68
    nym
    0.66
    нным
    0.66
    ческим
    0.65
    Act Density 0.002%

    No Known Activations