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

    Neuronpedia

    INDEX
    Explanations

    lax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Parcelize
    -0.89
     &___
    -0.84
     IndexPath
    -0.79
     للمعارف
    -0.75
    CreateModel
    -0.75
     Jaw
    -0.74
    rrggbb
    -0.73
     constipation
    -0.73
    RegistryLite
    -0.72
    MENAFN
    -0.72
    POSITIVE LOGITS
    line
    0.42
     PyTuple
    0.39
    mane
    0.36
    zości
    0.36
     met
    0.35
    forward
    0.35
    g
    0.35
    -
    0.34
    大家
    0.34
     efe
    0.33
    Act Density 0.023%

    No Known Activations