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

    Neuronpedia

    INDEX
    Explanations

    JVM

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hoc
    -0.08
     did
    -0.07
     cái
    -0.07
     Grace
    -0.07
    бро
    -0.07
     Et
    -0.07
     RIP
    -0.07
    崛
    -0.06
    idency
    -0.06
    羰
    -0.06
    POSITIVE LOGITS
    ‗
    0.07
    ☡
    0.07
    不应
    0.07
    -pane
    0.07
     Defaults
    0.07
     Ram
    0.07
    לות
    0.06
     ow
    0.06
     vết
    0.06
    )>=
    0.06
    Act Density 0.000%

    No Known Activations