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

    Neuronpedia

    INDEX
    Explanations

    location names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SIGN
    -0.07
     أي
    -0.07
     terr
    -0.07
    .P
    -0.07
     PER
    -0.07
    为大家
    -0.07
    ﺀ
    -0.07
     K
    -0.07
     gun
    -0.07
     bt
    -0.06
    POSITIVE LOGITS
    ﳏ
    0.07
    𬶐
    0.07
     richer
    0.07
     ogni
    0.07
    饮用
    0.07
    分かり
    0.07
    舣
    0.07
    .related
    0.07
    묻
    0.06
     mastery
    0.06
    Act Density 0.037%

    No Known Activations