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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Instances
    -0.07
    -used
    -0.06
     cabinets
    -0.06
     Sty
    -0.06
     Jer
    -0.06
    ot
    -0.06
    onyms
    -0.05
    ocused
    -0.05
     Mess
    -0.05
    Role
    -0.05
    POSITIVE LOGITS
    azine
    0.06
     önüne
    0.06
     perché
    0.06
    verified
    0.06
    _pemb
    0.06
    ivered
    0.06
     superb
    0.06
    $sql
    0.06
    Temporal
    0.06
    ']],↵
    0.06
    Act Density 0.176%

    No Known Activations