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

    Neuronpedia

    INDEX
    Explanations

    probation period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posición
    0.72
    '
    0.70
     institución
    0.67
     conexión
    0.67
     thụ
    0.64
     giardino
    0.64
     primi
    0.61
    ដើម្បី
    0.61
     alimentación
    0.61
     tjän
    0.61
    POSITIVE LOGITS
    A
    0.75
    N
    0.72
    Hb
    0.71
     Probation
    0.69
    س
    0.67
    াদা
    0.66
    Idents
    0.65
    AUC
    0.64
     kilobytes
    0.64
    W
    0.63
    Act Density 0.000%

    No Known Activations