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

    Neuronpedia

    INDEX
    Explanations

    Crosswords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rules
    -0.08
    ayd
    -0.07
    annonce
    -0.07
     STAT
    -0.06
     सत
    -0.06
    级
    -0.06
    powers
    -0.06
     POW
    -0.06
     κυ
    -0.06
     slam
    -0.06
    POSITIVE LOGITS
    vx
    0.08
     Mitsubishi
    0.08
    ubishi
    0.07
    .insert
    0.07
    らず
    0.06
    .Movie
    0.06
     Fran
    0.06
     calidad
    0.06
    appointed
    0.06
    getSize
    0.06
    Act Density 0.009%

    No Known Activations