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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     instinct
    -0.07
    $item
    -0.07
     abund
    -0.06
     evolved
    -0.06
     мыш
    -0.06
     Birth
    -0.06
     Liberties
    -0.06
    andidates
    -0.06
     dedicate
    -0.06
    _pr
    -0.06
    POSITIVE LOGITS
    λια
    0.07
    PF
    0.06
    414
    0.06
    (parse
    0.06
    (Operation
    0.06
     Dun
    0.06
    Ale
    0.06
    746
    0.06
    텔
    0.06
    стория
    0.06
    Act Density 0.000%

    No Known Activations