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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.62
     Ellos
    -0.53
     TestBed
    -0.47
    </code>
    -0.45
     surla
    -0.45
     acqu
    -0.44
     tỏ
    -0.44
     autob
    -0.43
     dul
    -0.43
     Dutt
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.68
     estekak
    0.67
    fjspx
    0.66
     vœux
    0.66
     extérieures
    0.66
     démocr
    0.66
     hâte
    0.63
     élas
    0.61
    apunov
    0.59
    writeFieldEnd
    0.59
    Act Density 0.003%

    No Known Activations