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

    Neuronpedia

    INDEX
    Explanations

    code symbols and multilingual characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ers
    0.41
     cognitive
    0.36
     ofer
    0.35
     condesc
    0.35
     softening
    0.34
     laufen
    0.34
     contraction
    0.33
     disproportion
    0.33
     cynical
    0.33
     domesticated
    0.33
    POSITIVE LOGITS
    0.44
    0.42
    0.41
    অত
    0.39
    }(
    0.38
     //
    0.38
    ילים
    0.38
     এসব
    0.37
    如果
    0.37
    Executor
    0.37
    Act Density 0.519%

    No Known Activations