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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    光
    -0.07
    voir
    -0.07
     testcase
    -0.07
     casual
    -0.06
     mænd
    -0.06
    ague
    -0.06
     гро
    -0.06
    aları
    -0.06
     meaning
    -0.06
     fiat
    -0.06
    POSITIVE LOGITS
    (food
    0.06
     Vi
    0.06
     Farrell
    0.06
     IndexPath
    0.06
    _pose
    0.06
    Slim
    0.06
     Majority
    0.06
     Pane
    0.06
    ไม
    0.06
     nový
    0.06
    Act Density 0.000%

    No Known Activations