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

    Neuronpedia

    INDEX
    Explanations

    effects, analysis, or sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ausz
    0.48
     An
    0.47
     ܗ
    0.47
     Thirdly
    0.47
     bea
    0.45
     Gest
    0.44
     Erect
    0.44
     Plugins
    0.43
     Even
    0.42
     lanz
    0.42
    POSITIVE LOGITS
    ні
    0.61
     온도
    0.55
    вес
    0.52
    ста
    0.49
    тельному
    0.48
    оборот
    0.47
    ъек
    0.46
    異なります
    0.46
    ilgan
    0.45
    agregar
    0.45
    Act Density 0.001%

    No Known Activations