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

    Neuronpedia

    INDEX
    Explanations

    sexual assault hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jefe
    0.79
    毌
    0.76
    ☻
    0.73
     propri
    0.70
     enemigos
    0.70
    ⬥
    0.69
    穰
    0.67
     ffilm
    0.67
    пами
    0.67
    gars
    0.67
    POSITIVE LOGITS
    short
    1.02
     short
    1.00
     Inf
    0.98
     inf
    0.96
    Short
    0.96
    Inf
    0.95
     INF
    0.90
     cleanup
    0.89
     corner
    0.86
     Short
    0.86
    Act Density 0.054%

    No Known Activations