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

    Neuronpedia

    INDEX
    Explanations

    local variable names

    oai_token-act-pair · gemini-2.0-flash

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lenker
    -0.81
    CompleteListener
    -0.73
     nakalista
    -0.68
     defaultstate
    -0.68
    mybatisplus
    -0.67
     []:
    -0.66
     transfieras
    -0.64
    })->
    -0.63
     ISNI
    -0.63
    Lycka
    -0.63
    POSITIVE LOGITS
    <bos>
    0.52
    ↵↵
    0.48
     marge
    0.48
    V
    0.47
     Investigaciones
    0.43
    in
    0.43
    (
    0.43
     Authors
    0.43
     o
    0.42
     Schatz
    0.42
    Act Density 4.701%

    No Known Activations