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

    Neuronpedia

    INDEX
    Explanations

    noble

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     okres
    -0.06
     등을
    -0.06
     (),
    -0.06
     scanned
    -0.06
     ()
    -0.06
     Ukr
    -0.06
     obrov
    -0.06
     iteration
    -0.06
    (mx
    -0.06
    σφα
    -0.06
    POSITIVE LOGITS
     Programme
    0.08
     Hall
    0.07
    able
    0.07
    listed
    0.07
    Hall
    0.07
     Noble
    0.07
    �
    0.07
     noble
    0.07
    .Root
    0.07
    material
    0.06
    Act Density 0.005%

    No Known Activations