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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xFD
    -0.08
    ("")↵
    -0.07
    นวน
    -0.06
    ۳۶
    -0.06
    VD
    -0.06
    jective
    -0.06
    еры
    -0.06
     równ
    -0.06
    92
    -0.06
    елю
    -0.06
    POSITIVE LOGITS
    .rest
    0.07
     disadv
    0.07
     yi
    0.07
     insanely
    0.07
     kho
    0.07
     AppState
    0.07
     amour
    0.07
     cbd
    0.06
     nuestros
    0.06
     mám
    0.06
    Act Density 0.047%

    No Known Activations