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

    Neuronpedia

    INDEX
    Explanations

    work tasks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     Collapse
    -0.06
    </
    -0.06
    otron
    -0.06
    ums
    -0.06
    #================================================================
    -0.06
     opp
    -0.06
    _unlock
    -0.06
    vable
    -0.06
    olocation
    -0.06
    POSITIVE LOGITS
     yytype
    0.07
     борь
    0.07
     Nasıl
    0.07
    .str
    0.07
     San
    0.06
    arsimp
    0.06
     Chunk
    0.06
    (priv
    0.06
     elo
    0.06
    FILE
    0.06
    Act Density 0.092%

    No Known Activations