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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    locker
    -0.07
     Valent
    -0.07
    ので
    -0.07
     [{'
    -0.07
    де
    -0.06
    speech
    -0.06
    casting
    -0.06
    rbrace
    -0.06
     sdl
    -0.06
     Gerard
    -0.06
    POSITIVE LOGITS
    ritte
    0.06
     Canada
    0.06
    ulia
    0.06
     Picasso
    0.06
    NotFoundException
    0.06
     cravings
    0.06
    ισμός
    0.06
    ические
    0.06
    éra
    0.06
     RBI
    0.06
    Act Density 0.001%

    No Known Activations