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

    Neuronpedia

    INDEX
    Explanations

    contracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SEG
    -0.07
    SEG
    -0.07
     Cher
    -0.07
    ์พ
    -0.06
    ального
    -0.06
     mak
    -0.06
    ercul
    -0.06
     Window
    -0.06
    thouse
    -0.06
     mou
    -0.06
    POSITIVE LOGITS
    /material
    0.06
    Weight
    0.06
     Coronavirus
    0.06
    _repeat
    0.06
     Lehr
    0.06
     kms
    0.05
    .Butter
    0.05
    иплом
    0.05
    .template
    0.05
    hotmail
    0.05
    Act Density 0.142%

    No Known Activations