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

    Neuronpedia

    INDEX
    Explanations

    roles and participants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    實
    -0.07
     mismo
    -0.07
    _bi
    -0.06
    Ny
    -0.06
     nicer
    -0.06
    ˆ
    -0.06
     weakened
    -0.06
    quat
    -0.06
     Sanat
    -0.06
    实
    -0.06
    POSITIVE LOGITS
    僅
    0.07
    **
↵
    0.06
     shout
    0.06
     Rivers
    0.06
    ão
    0.06
    ampion
    0.06
     lieutenant
    0.06
    under
    0.06
     vill
    0.06
    .EventArgs
    0.06
    Act Density 0.118%

    No Known Activations