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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oğ
    -0.07
     equals
    -0.07
     second
    -0.07
    Dashboard
    -0.06
     skyrocket
    -0.06
     protections
    -0.06
    _given
    -0.06
     disgr
    -0.06
     Dashboard
    -0.06
    .maximum
    -0.06
    POSITIVE LOGITS
     rua
    0.07
    @media
    0.06
    845
    0.06
    <"
    0.06
     нічого
    0.06
    <style
    0.06
    ‌انبار
    0.06
     обра
    0.06
    Href
    0.06
     lorem
    0.06
    Act Density 0.007%

    No Known Activations