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

    Neuronpedia

    INDEX
    Explanations

    harmful acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     προς
    0.77
     Founders
    0.71
    ž
    0.70
     наси
    0.70
     Benefits
    0.69
     !}\
    0.68
     GPL
    0.68
    onnées
    0.68
     Κο
    0.68
     volont
    0.67
    POSITIVE LOGITS
     casilla
    0.82
     elects
    0.76
     carcinomas
    0.75
     setembro
    0.75
     alleles
    0.75
     nowego
    0.74
     majd
    0.73
     parceria
    0.73
     awfully
    0.72
    ]{
    0.70
    Act Density 0.000%

    No Known Activations