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

    Neuronpedia

    INDEX
    Explanations

    phrases frequently used at the start of conversational tangents by a person giving advice

    oai_token-act-pair · gemini-2.0-flash

    Conversational, asides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.63
    HasMaxLength
    -0.62
    thâu
    -0.60
    nodoc
    -0.59
    meln
    -0.59
    parsedMessage
    -0.57
     Roskov
    -0.55
    цезда
    -0.54
     Wicidata
    -0.52
     生命周期
    -0.52
    POSITIVE LOGITS
    fjspx
    0.41
    ورن
    0.38
    ISM
    0.37
     istore
    0.37
    gimento
    0.36
    ̣
    0.36
    >>()
    0.36
     Pope
    0.36
    irsk
    0.35
    anti
    0.35
    Act Density 0.148%

    No Known Activations