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

    Neuronpedia

    INDEX
    Explanations

    date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .setEnabled
    -0.08
     clouds
    -0.07
     stabbing
    -0.07
     rep
    -0.06
    erial
    -0.06
    เบ
    -0.06
     splice
    -0.06
     feet
    -0.06
     adversaries
    -0.06
     Coil
    -0.06
    POSITIVE LOGITS
    0.06
    ("%
    0.06
    _SY
    0.06
     мас
    0.06
    *self
    0.06
    орту
    0.06
    *dt
    0.06
     dalam
    0.06
    ­های
    0.06
    Movement
    0.06
    Act Density 0.017%

    No Known Activations