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

    Neuronpedia

    INDEX
    Explanations

    commit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stored
    -0.07
     roasted
    -0.06
     brom
    -0.06
    .old
    -0.06
     bathing
    -0.06
     Assessment
    -0.06
     smoked
    -0.06
     folds
    -0.06
     Бог
    -0.06
     EDM
    -0.06
    POSITIVE LOGITS
    dg
    0.07
    assa
    0.07
    ecal
    0.07
    (sync
    0.06
    нить
    0.06
    جز
    0.06
     legally
    0.06
    noc
    0.06
     cater
    0.06
    (iter
    0.06
    Act Density 0.003%

    No Known Activations