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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     наиболее
    -0.07
    /base
    -0.06
    _ten
    -0.06
     modulo
    -0.06
    Contains
    -0.06
     تای
    -0.06
     tranny
    -0.06
     Reference
    -0.06
     newIndex
    -0.06
    .Reference
    -0.06
    POSITIVE LOGITS
    fred
    0.07
    فات
    0.06
    .instructions
    0.06
    wrap
    0.06
    망
    0.06
    ospace
    0.06
     bied
    0.06
    ━�
    0.06
    ellan
    0.06
    える
    0.06
    Act Density 0.065%

    No Known Activations