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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Request
    -0.08
    	cnt
    -0.07
     dále
    -0.06
    .paging
    -0.06
    (pb
    -0.06
    .Private
    -0.06
     получ
    -0.06
    recent
    -0.06
     most
    -0.06
    449
    -0.06
    POSITIVE LOGITS
     دست
    0.07
    さら
    0.06
     comrades
    0.06
    reve
    0.06
    riding
    0.06
    ansi
    0.06
     اه
    0.06
     Netanyahu
    0.06
     registering
    0.06
     sé
    0.06
    Act Density 0.027%

    No Known Activations