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
     classroom
    -0.07
    118
    -0.07
     Παρ
    -0.07
    (p
    -0.06
     credit
    -0.06
    Laura
    -0.06
    iden
    -0.06
    _it
    -0.06
     boundary
    -0.06
     journals
    -0.06
    POSITIVE LOGITS
     近
    0.07
    istrovství
    0.06
    UPPORT
    0.06
     vec
    0.06
     Monroe
    0.06
     méth
    0.06
    BigInt
    0.06
     nemovit
    0.06
     UBND
    0.06
     proliferation
    0.06
    Act Density 0.005%

    No Known Activations