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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NATIONAL
    -0.07
    peating
    -0.07
     Sector
    -0.06
     pod
    -0.06
    central
    -0.06
    PI
    -0.06
    VIS
    -0.06
     Lena
    -0.06
     grupos
    -0.06
    ниць
    -0.06
    POSITIVE LOGITS
    He
    0.07
    ")]↵↵
    0.06
    需要
    0.06
    claimer
    0.06
    _EM
    0.06
    ，更
    0.06
    ,temp
    0.06
    更
    0.06
    .direct
    0.06
    ,left
    0.06
    Act Density 0.012%

    No Known Activations