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

    Neuronpedia

    INDEX
    Explanations

    float

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Severity
    -0.07
     oven
    -0.07
     messageId
    -0.07
    子
    -0.07
     Oven
    -0.07
     texts
    -0.07
    (shift
    -0.06
     Arbitrary
    -0.06
    hotel
    -0.06
     notices
    -0.06
    POSITIVE LOGITS
    ROTO
    0.06
    イル
    0.06
     bị
    0.06
    ofilm
    0.06
    !!
    0.06
    ічних
    0.06
    :flex
    0.06
    (Il
    0.06
     بل
    0.06
    ，可以
    0.06
    Act Density 0.002%

    No Known Activations