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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Ad
    -0.08
    ossip
    -0.07
     lizard
    -0.07
     bar
    -0.07
    ouncil
    -0.07
     florida
    -0.06
     aesthetic
    -0.06
    -f
    -0.06
    ventions
    -0.06
    ossa
    -0.06
    POSITIVE LOGITS
    .iloc
    0.07
    _BITMAP
    0.07
    λης
    0.06
     kInstruction
    0.06
     @[
    0.06
     Uk
    0.06
     засобів
    0.06
    Dlg
    0.06
    _FOUND
    0.06
     NgModule
    0.06
    Act Density 0.031%

    No Known Activations