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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emento
    -0.07
    .proj
    -0.06
    zilla
    -0.06
     Shack
    -0.06
    <number
    -0.06
    _warning
    -0.06
    怪
    -0.06
    -world
    -0.06
    otle
    -0.06
     certs
    -0.06
    POSITIVE LOGITS
     over
    0.08
    释
    0.06
     koc
    0.06
    >();
    0.06
     열
    0.06
     elegance
    0.06
     Iron
    0.06
     Roh
    0.06
     OVER
    0.06
    osition
    0.06
    Act Density 0.016%

    No Known Activations