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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     referenties
    -0.73
    AndEndTag
    -0.66
    uxxxx
    -0.59
    principalTable
    -0.53
     erklär
    -0.51
    hdysval
    -0.51
    ือง
    -0.50
    ake
    -0.50
     engineering
    -0.49
     сочи
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.68
     serai
    0.58
     Cutting
    0.56
     cutting
    0.54
    Cutting
    0.54
     Cel
    0.53
    MENAFN
    0.53
     ujednoznacz
    0.51
     cle
    0.50
    CPtr
    0.50
    Act Density 0.001%

    No Known Activations