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

    Neuronpedia

    INDEX
    Explanations

    increase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tracking
    -0.08
    kle
    -0.07
     extent
    -0.07
    arak
    -0.07
     kadar
    -0.06
     bölüm
    -0.06
    裁
    -0.06
     turret
    -0.06
     전
    -0.06
    бас
    -0.06
    POSITIVE LOGITS
    -heavy
    0.07
     Scre
    0.07
     �
    0.07
    災
    0.06
     Conscious
    0.06
    \Mapping
    0.06
    _SD
    0.06
    <()>
    0.06
     reinforcing
    0.06
     thị
    0.06
    Act Density 0.005%

    No Known Activations