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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /document
    -0.07
    ehen
    -0.07
    ってきた
    -0.07
     erotiske
    -0.06
    -browser
    -0.06
     dolls
    -0.06
    rote
    -0.06
    .converter
    -0.06
    anske
    -0.06
    ейн
    -0.06
    POSITIVE LOGITS
    JOB
    0.06
    alta
    0.06
    QN
    0.06
    ::*;↵↵
    0.06
     Q
    0.06
    press
    0.06
     embar
    0.06
     chose
    0.06
     condos
    0.06
     respects
    0.06
    Act Density 0.076%

    No Known Activations