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

    Neuronpedia

    INDEX
    Explanations

    multiplication symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     जिंदगी
    -0.08
    akit
    -0.08
    _HIDE
    -0.07
     violência
    -0.07
     Strike
    -0.07
     Northwestern
    -0.07
    communications
    -0.07
     gyven
    -0.07
    ชีวิต
    -0.07
     Northern
    -0.07
    POSITIVE LOGITS
     jeweils
    0.10
     halves
    0.09
     fach
    0.08
     fails
    0.07
     detachable
    0.07
    配置
    0.07
     opa
    0.07
     piece
    0.07
     મળશે
    0.07
    фер
    0.07
    Act Density 0.008%

    No Known Activations