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

    Neuronpedia

    INDEX
    Explanations

    specific requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plugin
    0.42
    ：（
    0.42
     cie
    0.41
    vio
    0.40
    plugin
    0.39
     uniq
    0.38
     Commun
    0.38
     assemble
    0.38
    azan
    0.37
     assembly
    0.37
    POSITIVE LOGITS
     உடன்
    0.43
    Editar
    0.42
     конститу
    0.40
    頊
    0.40
    iraj
    0.38
     κε
    0.37
    に行く
    0.37
     править
    0.37
     megy
    0.36
     î
    0.36
    Act Density 0.000%

    No Known Activations