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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    726
    -0.07
     swords
    -0.07
    _fast
    -0.07
    /lg
    -0.06
    çu
    -0.06
    ifu
    -0.06
    нула
    -0.06
    议
    -0.06
    hydrate
    -0.06
    力量
    -0.06
    POSITIVE LOGITS
     getOrder
    0.06
    ultiply
    0.06
     contrace
    0.06
     Emb
    0.06
    .FlatAppearance
    0.06
    >.</
    0.06
    Access
    0.06
     op
    0.06
    De
    0.06
     Venue
    0.06
    Act Density 0.004%

    No Known Activations