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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     порядке
    -0.07
     banging
    -0.07
    phase
    -0.06
    肉
    -0.06
    叫
    -0.06
     consuming
    -0.06
    ka
    -0.06
     Sciences
    -0.06
     Typically
    -0.06
    grading
    -0.06
    POSITIVE LOGITS
     neigh
    0.06
    licing
    0.06
     bmi
    0.06
    .pivot
    0.06
    .Task
    0.06
    undler
    0.06
    .IMAGE
    0.06
     TIMEOUT
    0.06
    IELD
    0.06
    ="@
    0.06
    Act Density 0.027%

    No Known Activations