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

    Neuronpedia

    INDEX
    Explanations

    hidden

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     necessary
    -0.08
     meilleurs
    -0.08
     необходимые
    -0.08
     хороший
    -0.08
     melhores
    -0.08
     полез
    -0.08
     福利
    -0.08
    sad
    -0.08
     тези
    -0.08
     可
    -0.08
    POSITIVE LOGITS
     Hidden
    0.13
     lurking
    0.12
    Hidden
    0.12
     hidden
    0.12
     overlooked
    0.11
    hidden
    0.10
    _hidden
    0.10
     unsus
    0.10
    .hidden
    0.10
     unnoticed
    0.10
    Act Density 0.052%

    No Known Activations