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

    Neuronpedia

    INDEX
    Explanations

    IDENTITY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gada
    0.53
    dı
    0.53
    )")
    0.52
    )((
    0.52
    onej
    0.50
    cut
    0.50
    cimiento
    0.50
    teile
    0.49
    di
    0.48
    kiego
    0.47
    POSITIVE LOGITS
     hypothes
    0.48
    有什么
    0.45
     Minority
    0.44
     it
    0.42
     hydroly
    0.42
     pequenas
    0.41
     Lehigh
    0.41
     high
    0.40
    స్య
    0.40
     kazi
    0.40
    Act Density 0.005%

    No Known Activations