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

    Neuronpedia

    INDEX
    Explanations

    't

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    废水
    -0.08
    -wide
    -0.07
     Specs
    -0.07
     screws
    -0.07
    Less
    -0.07
    openhagen
    -0.07
    peg
    -0.07
    .Edit
    -0.07
    镜子
    -0.07
    gee
    -0.07
    POSITIVE LOGITS
    立足
    0.07
     '\'
    0.07
     loung
    0.07
    来回
    0.07
    出生
    0.07
    .internet
    0.06
    平凡
    0.06
     Rol
    0.06
    hon
    0.06
    _BLOCK
    0.06
    Act Density 0.006%

    No Known Activations