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

    Neuronpedia

    INDEX
    Explanations

    Code and log excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yeri
    -0.07
     مسئ
    -0.07
    府
    -0.06
    เฮ
    -0.06
    ровер
    -0.06
    _phase
    -0.06
    .FileWriter
    -0.06
    .sky
    -0.06
    recipient
    -0.06
    팔
    -0.06
    POSITIVE LOGITS
     -(
    0.08
    ammed
    0.07
    jure
    0.07
    irmed
    0.07
    CTOR
    0.06
    vla
    0.06
    (plot
    0.06
     smo
    0.06
    appen
    0.06
    스티
    0.06
    Act Density 0.067%

    No Known Activations