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

    Neuronpedia

    INDEX
    Explanations

    based location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ం
    0.96
     económicas
    0.96
    개의
    0.95
     liberación
    0.94
     және
    0.93
    트
    0.92
     данные
    0.91
     compleja
    0.91
    ו
    0.91
     declaraciones
    0.91
    POSITIVE LOGITS
    ليزية
    0.87
    mar
    0.86
    s
    0.84
    schnitt
    0.84
    surface
    0.83
    system
    0.82
    naval
    0.82
    \,.
    0.82
    ue
    0.81
    sensors
    0.81
    Act Density 0.000%

    No Known Activations