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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    したら
    -0.07
    _star
    -0.07
    yard
    -0.07
    ooting
    -0.07
     Charter
    -0.06
     Schwarz
    -0.06
     Gladiator
    -0.06
     ZERO
    -0.06
     birlikte
    -0.06
     Semester
    -0.06
    POSITIVE LOGITS
    alten
    0.07
    刻
    0.06
    -net
    0.06
     baise
    0.06
     divided
    0.06
    (owner
    0.06
    dns
    0.06
     stained
    0.06
    ază
    0.06
    ево
    0.06
    Act Density 0.030%

    No Known Activations