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

    Neuronpedia

    INDEX
    Explanations

    500

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crist
    -0.06
    ��
    -0.06
    杰
    -0.06
     downfall
    -0.06
    crop
    -0.06
    bek
    -0.06
     Αρχ
    -0.05
    판
    -0.05
     visited
    -0.05
    Stored
    -0.05
    POSITIVE LOGITS
     Його
    0.07
    (columns
    0.07
     pedal
    0.07
     Vec
    0.07
     Polynomial
    0.07
    _RESET
    0.07
    uniacid
    0.06
     Literal
    0.06
     boob
    0.06
     Strat
    0.06
    Act Density 0.004%

    No Known Activations