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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DAN
    -0.07
     wah
    -0.06
     elevation
    -0.06
    ,,
    -0.06
     {{{
    -0.06
    ISOString
    -0.06
    _ip
    -0.06
     Muss
    -0.06
     alignment
    -0.06
    TextBoxColumn
    -0.05
    POSITIVE LOGITS
     Manor
    0.26
    or
    0.10
    orr
    0.07
     tractor
    0.07
    ريم
    0.07
    essages
    0.07
    arr
    0.07
    ctor
    0.07
     Phoenix
    0.07
    ori
    0.07
    Act Density 0.002%

    No Known Activations