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

    Neuronpedia

    INDEX
    Explanations

    variable assignment and usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     serializers
    0.83
     পূর্ববাংলা
    0.82
     prothorax
    0.79
    燾
    0.77
    чої
    0.76
     pós
    0.76
     oxígeno
    0.76
    icleta
    0.75
     postice
    0.74
     rampant
    0.73
    POSITIVE LOGITS
    [$
    1.10
     ($
    0.98
    *$
    0.97
    array
    0.97
    ($
    0.95
     [$
    0.93
     $
    0.91
    =$
    0.90
    =>$
    0.90
    '],$
    0.89
    Act Density 0.155%

    No Known Activations