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

    Neuronpedia

    INDEX
    Explanations

    ac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )v
    -0.08
     можно
    -0.07
     mixing
    -0.07
     correction
    -0.06
    .radioButton
    -0.06
     stimulation
    -0.06
    locator
    -0.06
     lessons
    -0.06
    Controls
    -0.06
    rita
    -0.06
    POSITIVE LOGITS
     EXPRESS
    0.07
    akat
    0.07
    lemen
    0.06
     Alic
    0.06
     hdc
    0.06
    amics
    0.06
     zoekt
    0.06
    EMENT
    0.06
     �
    0.06
    ическим
    0.06
    Act Density 0.002%

    No Known Activations