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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -yyyy
    -0.08
    cona
    -0.07
    297
    -0.06
    cac
    -0.06
     amigos
    -0.06
    (adj
    -0.06
    ibil
    -0.06
    $rs
    -0.06
    раз
    -0.06
    _ART
    -0.05
    POSITIVE LOGITS
    форма
    0.07
     greenhouse
    0.07
    Table
    0.06
     plunge
    0.06
    >')
    0.06
     건
    0.06
     заним
    0.06
    PACKAGE
    0.06
     producers
    0.06
     unveiling
    0.06
    Act Density 0.012%

    No Known Activations