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

    Neuronpedia

    INDEX
    Explanations

    instances in a transcript where the speaker is reasoning through a problem and vocalizing their thought process

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abouts
    -0.07
     Seit
    -0.07
    and
    -0.07
    اد
    -0.06
    ná
    -0.06
    áo
    -0.06
    åĨ
    -0.06
    amp
    -0.06
    ãģ²
    -0.06
    ide
    -0.06
    POSITIVE LOGITS
    yonel
    0.09
    .scalablytyped
    0.08
    -lnd
    0.08
    галÑĸ
    0.07
    (Initialized
    0.07
    _tF
    0.07
    ÙĪÛĮÙĨت
    0.07
    GINE
    0.07
    ÛĮÛĮÙĨ
    0.07
     ↵↵
    0.07
    Act Density 0.974%

    No Known Activations