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

    Neuronpedia

    INDEX
    Explanations

    say "the ending ."

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glob
    -0.08
     logout
    -0.07
    欠缺
    -0.07
    之势
    -0.07
    依赖
    -0.07
    .art
    -0.06
     dy
    -0.06
    打扰
    -0.06
     Todo
    -0.06
    young
    -0.06
    POSITIVE LOGITS
    (i
    0.06
    vertise
    0.06
    educt
    0.06
    oretical
    0.06
    𬳵
    0.06
    .getLabel
    0.06
    います
    0.06
    _REFER
    0.06
    ţi
    0.06
     заболев
    0.06
    Act Density 0.110%

    No Known Activations