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

    Neuronpedia

    INDEX
    Explanations

    online resources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uka
    -0.07
    央视
    -0.07
    baseUrl
    -0.07
     Hor
    -0.06
     chociaż
    -0.06
    ']).
    -0.06
    ])->
    -0.06
    -0.06
     mujeres
    -0.06
    RB
    -0.06
    POSITIVE LOGITS
     Presbyterian
    0.07
    ship
    0.07
    分管
    0.07
    -thread
    0.07
    理智
    0.07
     shar
    0.07
    _detach
    0.07
    _OTHER
    0.07
    쭈
    0.07
    ㄍ
    0.07
    Act Density 0.031%

    No Known Activations