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

    Neuronpedia

    INDEX
    Explanations

    changes by teams/users

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alta
    -0.08
    _spinner
    -0.07
     шир
    -0.07
     참
    -0.07
     cancel
    -0.06
    .edit
    -0.06
     Numerous
    -0.06
    andas
    -0.06
    넥
    -0.06
    Connecting
    -0.06
    POSITIVE LOGITS
    -comm
    0.07
    versation
    0.07
    cover
    0.07
    TREE
    0.07
    .function
    0.07
    -fe
    0.07
    úsqueda
    0.06
    馄
    0.06
    崩
    0.06
    믄
    0.06
    Act Density 0.281%

    No Known Activations