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

    Neuronpedia

    INDEX
    Explanations

    superlative comparisons.

    oai_token-act-pair · gemini-2.0-flash

    Exceeding expectations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     own
    -0.49
    具
    -0.46
     first
    -0.45
     تانيه
    -0.44
     other
    -0.44
    ded
    -0.42
     second
    -0.42
    гер
    -0.42
    sidemargin
    -0.42
    yse
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.82
    +#+#
    0.68
    DockStyle
    0.64
    شهاد
    0.63
    +:+
    0.63
     publiques
    0.61
    seamnă
    0.61
    脚注の使い方
    0.60
     estekak
    0.60
     morire
    0.59
    Act Density 0.199%

    No Known Activations