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

    Neuronpedia

    INDEX
    Explanations

    Pipkin Merry Gaffer Northwestern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uin
    0.12
    にかく
    0.12
    ಿಗಳ
    0.12
     “…
    0.12
     バイ
    0.12
     Maguire
    0.12
    lytres
    0.12
    क़्त
    0.12
    পত্র
    0.12
     पड़े
    0.12
    POSITIVE LOGITS
    5
    0.14
    dw
    0.13
    Previously
    0.13
    <
    0.13
    9
    0.12
    Safety
    0.12
    8
    0.12
    Blend
    0.12
     blend
    0.12
     precession
    0.12
    Act Density 0.002%

    No Known Activations