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

    Neuronpedia

    INDEX
    Explanations

    normal communication based on relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qy
    0.39
    ails
    0.37
     undef
    0.36
    idders
    0.35
     आकर्
    0.35
    ",{
    0.35
    okit
    0.34
    oxy
    0.34
     Spe
    0.33
    gings
    0.33
    POSITIVE LOGITS
     normally
    2.02
     Normally
    1.82
    normally
    1.79
     habituellement
    1.77
     normalmente
    1.76
    Normally
    1.75
     обычно
    1.74
     normalerweise
    1.72
     usually
    1.66
     عادة
    1.64
    Act Density 0.021%

    No Known Activations