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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    מ
    0.46
    ﺮ
    0.46
    ༨
    0.46
     ។
    0.45
     negozio
    0.45
     ஏற்படுகிறது
    0.45
    ји
    0.44
    جات
    0.44
    prits
    0.44
    Jadi
    0.44
    POSITIVE LOGITS
     elucidated
    0.51
     elucid
    0.51
     enzym
    0.46
     Strategy
    0.45
     Jupyter
    0.45
     exemplar
    0.44
     Enzym
    0.44
     Begin
    0.43
     analogous
    0.43
     Debug
    0.43
    Act Density 0.005%

    No Known Activations