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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oks
    -0.08
     Child
    -0.07
    切换
    -0.07
    health
    -0.07
    fid
    -0.07
    ❄
    -0.07
    大家
    -0.07
    _ac
    -0.06
     Bella
    -0.06
    hapus
    -0.06
    POSITIVE LOGITS
    佁
    0.07
    .offer
    0.07
    롑
    0.07
    תיבת
    0.07
    .PathVariable
    0.07
     policym
    0.07
    �
    0.06
    .IsDBNull
    0.06
    OMATIC
    0.06
    /if
    0.06
    Act Density 0.011%

    No Known Activations