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

    Neuronpedia

    INDEX
    Explanations

    identification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    什么事
    -0.07
    /ns
    -0.07
    (runtime
    -0.07
    pared
    -0.07
    rys
    -0.07
    失信
    -0.07
    yne
    -0.07
    某种
    -0.07
    ᲂ
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    izados
    0.07
    とりあえ
    0.07
    *=
    0.07
    ]+"
    0.07
     shall
    0.07
    Defs
    0.07
    titleLabel
    0.07
     Hawks
    0.07
    わず
    0.07
    インター�
    0.06
    Act Density 0.015%

    No Known Activations