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

    Neuronpedia

    INDEX
    Explanations

    scientific articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Unknown
    -0.06
     indicative
    -0.06
    قى
    -0.06
    (resource
    -0.06
    .strip
    -0.06
     fierc
    -0.06
    ba
    -0.06
    gettext
    -0.06
    ाण
    -0.06
    edit
    -0.06
    POSITIVE LOGITS
     Wochen
    0.07
     cowork
    0.07
    larla
    0.06
     existential
    0.06
    elerle
    0.06
    .restore
    0.06
     fclose
    0.06
    .between
    0.06
    ่อ
    0.06
     schw
    0.06
    Act Density 0.016%

    No Known Activations