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

    Neuronpedia

    INDEX
    Explanations

    HTML

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chú
    -0.07
    棫
    -0.07
    خوف
    -0.07
    ep
    -0.06
    ﭬ
    -0.06
    스크
    -0.06
    鲃
    -0.06
     winger
    -0.06
    ck
    -0.06
    achi
    -0.06
    POSITIVE LOGITS
    _rand
    0.08
    0.07
    ]+\
    0.07
     stencil
    0.07
    0.07
    Rules
    0.07
    抽检
    0.07
    >().
    0.07
    Б
    0.07
    _IO
    0.07
    Act Density 0.000%

    No Known Activations