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

    Neuronpedia

    INDEX
    Explanations

    -mode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rail
    -0.07
    _dll
    -0.07
     celou
    -0.07
    endir
    -0.07
     Vir
    -0.06
     xen
    -0.06
     Spl
    -0.06
    oken
    -0.06
    urile
    -0.06
     Dont
    -0.06
    POSITIVE LOGITS
    SRC
    0.06
    ographics
    0.06
    атегор
    0.06
     consolidated
    0.06
    rodní
    0.06
    _TRNS
    0.06
    _alt
    0.06
    ]?
    0.06
     четвер
    0.05
     absorbed
    0.05
    Act Density 0.000%

    No Known Activations