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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    teş
    -0.07
     therapies
    -0.06
     clar
    -0.06
     сб
    -0.06
    有一
    -0.06
     embr
    -0.06
     Pek
    -0.06
    VR
    -0.05
    sanız
    -0.05
     ViewState
    -0.05
    POSITIVE LOGITS
    _PARAMETERS
    0.07
    ルの
    0.07
    NSNumber
    0.07
     airstrikes
    0.06
    hell
    0.06
    Space
    0.06
     Birds
    0.06
     Mess
    0.06
     girl
    0.06
    Access
    0.06
    Act Density 0.012%

    No Known Activations