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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contributors
    -0.08
    átis
    -0.07
    からは
    -0.06
     rever
    -0.06
    ザ
    -0.06
     tér
    -0.06
    _effect
    -0.06
    .hide
    -0.06
     án
    -0.06
    buch
    -0.06
    POSITIVE LOGITS
    στημα
    0.07
     casa
    0.07
    overlap
    0.06
     Bryant
    0.06
     SCE
    0.06
    とする
    0.06
    _utf
    0.06
     breaker
    0.06
    ssa
    0.06
     psychotic
    0.06
    Act Density 0.000%

    No Known Activations