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

    Neuronpedia

    INDEX
    Explanations

    .join

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pose
    -0.06
     rays
    -0.06
     میدان
    -0.06
    ration
    -0.06
     cyber
    -0.06
     LU
    -0.06
    _PM
    -0.06
    莉
    -0.06
    ＿＿
    -0.06
     외국
    -0.06
    POSITIVE LOGITS
    .join
    0.12
    (fullfile
    0.07
    ']){↵
    0.07
    ........................
    0.07
    ToLower
    0.06
     ALLOW
    0.06
     EXP
    0.06
     함께
    0.06
     кип
    0.06
     Nottingham
    0.06
    Act Density 0.001%

    No Known Activations