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

    Neuronpedia

    INDEX
    Explanations

    ------

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ![
    -0.06
     FAG
    -0.06
     ifs
    -0.06
    REDIS
    -0.06
    ![
    -0.06
     wart
    -0.06
     Sport
    -0.06
     程
    -0.06
     IMO
    -0.06
    _ent
    -0.06
    POSITIVE LOGITS
    222
    0.07
    енные
    0.06
     neredeyse
    0.06
    ALLENG
    0.06
    -single
    0.06
    属性
    0.06
    combination
    0.06
    association
    0.06
    REN
    0.06
     Instagram
    0.06
    Act Density 0.007%

    No Known Activations