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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heating
    -0.07
    "context
    -0.07
    PRESS
    -0.06
    -flight
    -0.06
    Normal
    -0.06
    .TextInput
    -0.06
    eted
    -0.06
    QN
    -0.06
     black
    -0.06
    مشاهدة
    -0.06
    POSITIVE LOGITS
    >`
    0.08
     Sensors
    0.07
    /rem
    0.07
     Cheng
    0.07
    (CONT
    0.06
    akedown
    0.06
     ownership
    0.06
    Kenn
    0.06
    _map
    0.06
    %,
    0.06
    Act Density 0.001%

    No Known Activations