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

    Neuronpedia

    INDEX
    Explanations

    разбираться, знать, предлагать, обращать внимание

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.66
    S
    0.65
     D
    0.63
    R
    0.63
     St
    0.62
     R
    0.60
     F
    0.59
    A
    0.59
     G
    0.57
    F
    0.57
    POSITIVE LOGITS
    carrito
    0.82
     мир
    0.79
     oln
    0.79
     только
    0.79
     herewith
    0.79
     именно
    0.78
     и
    0.78
     мо
    0.77
    mnu
    0.76
     castom
    0.75
    Act Density 0.073%

    No Known Activations