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

    Neuronpedia

    INDEX
    Explanations

    talking about people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fails
    -0.07
    /DTD
    -0.07
    胆固醇
    -0.07
    -aos
    -0.07
    ’ai
    -0.07
    放松
    -0.06
     геро
    -0.06
    ")]
↵
    -0.06
    .EXP
    -0.06
    .flat
    -0.06
    POSITIVE LOGITS
    多人
    0.07
    arker
    0.07
     Bracket
    0.07
     readable
    0.07
    这两个
    0.07
     Carol
    0.07
     Sommer
    0.07
    バッグ
    0.07
     career
    0.07
     manpower
    0.06
    Act Density 0.048%

    No Known Activations