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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _toggle
    -0.06
     FOR
    -0.06
    metry
    -0.06
     CSI
    -0.06
     fais
    -0.06
     пти
    -0.06
     plo
    -0.06
    ývá
    -0.06
     بندی
    -0.06
     تل
    -0.06
    POSITIVE LOGITS
    Billing
    0.06
    lâm
    0.06
    เทศ
    0.06
     thrilling
    0.06
    ired
    0.06
     DECLARE
    0.06
    ++++++++++++++++++++++++++++++++
    0.06
    �
    0.06
     Define
    0.06
     эти
    0.06
    Act Density 0.002%

    No Known Activations