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

    Neuronpedia

    INDEX
    Explanations

    requested

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thinking
    -0.07
    _PWM
    -0.07
     landlord
    -0.06
    idi
    -0.06
    ュ
    -0.06
    isers
    -0.06
    ouns
    -0.06
    리지
    -0.06
    �
    -0.06
    -work
    -0.06
    POSITIVE LOGITS
     Kennedy
    0.07
    Attention
    0.07
    creat
    0.07
     Lester
    0.06
    "E
    0.06
     Sample
    0.06
     Milli
    0.06
    ecko
    0.06
    (log
    0.06
    <G
    0.06
    Act Density 0.019%

    No Known Activations