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

    Neuronpedia

    INDEX
    Explanations

    scientific/medical publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    last
    -0.07
     teen
    -0.07
     בעיר
    -0.07
    每个人
    -0.07
     textBox
    -0.07
    _BEFORE
    -0.07
    עצמאות
    -0.07
     nex
    -0.07
    imeType
    -0.07
    ervations
    -0.07
    POSITIVE LOGITS
     willen
    0.07
     nichts
    0.07
     DIN
    0.06
    TYPO
    0.06
    gratis
    0.06
    توج
    0.06
     Million
    0.06
     Café
    0.06
    JT
    0.06
     yii
    0.06
    Act Density 0.371%

    No Known Activations