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

    Neuronpedia

    INDEX
    Explanations

    imports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ∑
    -0.07
    時間が
    -0.07
    _Act
    -0.07
    קצב
    -0.07
    כנע
    -0.07
    電
    -0.07
     MAN
    -0.07
     Vent
    -0.06
    Knight
    -0.06
    .depend
    -0.06
    POSITIVE LOGITS
    Loading
    0.09
    -thread
    0.07
    .Pull
    0.07
     Opport
    0.07
    Load
    0.07
    (blog
    0.07
     lr
    0.07
    ղ
    0.07
    lik
    0.07
    photo
    0.07
    Act Density 0.001%

    No Known Activations