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

    Neuronpedia

    INDEX
    Explanations

    al/ional endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ژاپ
    -0.07
     берез
    -0.07
     babe
    -0.06
    ％
    -0.06
    が出
    -0.06
    家伙
    -0.06
     lay
    -0.06
    <Sprite
    -0.06
    üyük
    -0.06
     unprecedented
    -0.06
    POSITIVE LOGITS
    ional
    0.10
    ational
    0.10
    ical
    0.09
    nal
    0.09
    al
    0.09
    AL
    0.09
    onal
    0.08
    orial
    0.08
     relational
    0.08
    ITAL
    0.08
    Act Density 0.045%

    No Known Activations