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

    Neuronpedia

    INDEX
    Explanations

    Monte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Produce
    -0.07
     etkil
    -0.07
    087
    -0.06
    218
    -0.06
     хвор
    -0.06
    řejmě
    -0.06
    avan
    -0.06
     двух
    -0.06
    _predicate
    -0.06
    utils
    -0.06
    POSITIVE LOGITS
    _Per
    0.07
    sandbox
    0.07
     pilgrimage
    0.06
     fün
    0.06
    ジェ
    0.06
     angi
    0.06
    θυ
    0.06
    Ster
    0.06
     instructional
    0.06
     presence
    0.06
    Act Density 0.004%

    No Known Activations