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

    Neuronpedia

    INDEX
    Explanations

    State

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尋
    -0.08
    三季度
    -0.07
    看起來
    -0.07
     rms
    -0.07
     hasil
    -0.07
    _ASM
    -0.07
    _inter
    -0.07
    どう
    -0.06
    ynn
    -0.06
    江南
    -0.06
    POSITIVE LOGITS
    _mgmt
    0.07
    ";//
    0.07
     ostat
    0.07
    ection
    0.07
    いただき
    0.07
    被誉
    0.07
     affects
    0.07
    рест
    0.07
    categorie
    0.07
     restrained
    0.07
    Act Density 0.007%

    No Known Activations