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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ith
    -0.06
     ["
    -0.06
    ζ
    -0.06
     "%.
    -0.06
     ribs
    -0.06
    ládání
    -0.06
     ห
    -0.06
    are
    -0.05
    kin
    -0.05
    ields
    -0.05
    POSITIVE LOGITS
    .Style
    0.08
     stalking
    0.08
    _GB
    0.07
     أبريل
    0.07
     ubic
    0.06
     Temperature
    0.06
    Redis
    0.06
     JIT
    0.06
    .mm
    0.06
     Assess
    0.06
    Act Density 0.147%

    No Known Activations