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

    Neuronpedia

    INDEX
    Explanations

    data input/output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     judged
    -0.06
    .smart
    -0.06
    irty
    -0.06
    Raise
    -0.05
     unin
    -0.05
     tractor
    -0.05
     surgeon
    -0.05
    neg
    -0.05
    applicant
    -0.05
     happiest
    -0.05
    POSITIVE LOGITS
     staple
    0.07
     plagued
    0.07
    .DataGridViewTriState
    0.07
    !,↵
    0.06
    .';↵
    0.06
    $/,
    0.06
    .Sequential
    0.06
     creampie
    0.06
     війни
    0.06
     darken
    0.06
    Act Density 0.027%

    No Known Activations