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

    Neuronpedia

    INDEX
    Explanations

    state or action followed by object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oficina
    0.98
     interessa
    0.98
     dilakukan
    0.98
    woorden
    0.97
     técnico
    0.95
    rania
    0.94
     inmediata
    0.93
    🏬
    0.93
     comunidad
    0.93
    aulay
    0.93
    POSITIVE LOGITS
    3
    0.79
    5
    0.75
    ALT
    0.74
    겹
    0.74
     War
    0.73
    ნის
    0.72
    War
    0.67
     WAR
    0.65
    Add
    0.65
    Wr
    0.65
    Act Density 0.000%

    No Known Activations