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

    Neuronpedia

    INDEX
    Explanations

    ё

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CSL
    -0.08
    攻关
    -0.07
    辖
    -0.07
    _flag
    -0.07
     lectures
    -0.07
    _k
    -0.07
    什么时候
    -0.07
    繞
    -0.07
    融资租赁
    -0.07
    .Inv
    -0.06
    POSITIVE LOGITS
    heed
    0.07
     cheats
    0.07
    Deaths
    0.07
     матч
    0.07
     세계
    0.07
    _Account
    0.06
    ihat
    0.06
    帰
    0.06
    情緒
    0.06
     Sexo
    0.06
    Act Density 0.003%

    No Known Activations