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

    Neuronpedia

    INDEX
    Explanations

    US presidents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Encryption
    -0.08
     surgeon
    -0.07
     кораб
    -0.07
    萬
    -0.06
    cılık
    -0.06
    ampiyon
    -0.06
    .node
    -0.06
     interpreting
    -0.06
     Crowd
    -0.06
    -good
    -0.06
    POSITIVE LOGITS
    십
    0.06
    617
    0.06
    ToListAsync
    0.06
    ‐-
    0.06
    mít
    0.05
    �
    0.05
    สมาช
    0.05
    ayscale
    0.05
     maken
    0.05
    LIBINT
    0.05
    Act Density 0.031%

    No Known Activations