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

    Neuronpedia

    INDEX
    Explanations

    reduce or minimize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iers
    0.43
    pean
    0.41
    amel
    0.39
    erna
    0.39
    era
    0.38
    rowski
    0.38
    pes
    0.37
    媒体
    0.37
     RM
    0.36
    amientos
    0.36
    POSITIVE LOGITS
     Palms
    0.43
    isEnabled
    0.40
    വിഡ്
    0.40
     Hauptstadt
    0.40
     ssid
    0.39
     cubs
    0.38
     eigenvalue
    0.38
     SSID
    0.38
     negativo
    0.37
     Palmas
    0.37
    Act Density 0.001%

    No Known Activations