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

    Neuronpedia

    INDEX
    Explanations

    along

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dimit
    -0.06
     Canyon
    -0.06
    .goal
    -0.06
     Pasta
    -0.06
    outfile
    -0.05
     Legend
    -0.05
    opr
    -0.05
    recall
    -0.05
     ISS
    -0.05
    ewidth
    -0.05
    POSITIVE LOGITS
    (de
    0.07
     England
    0.07
    asbourg
    0.07
    (Role
    0.07
     flats
    0.07
    (Code
    0.06
    (Fl
    0.06
    (Web
    0.06
     scand
    0.06
    _SEG
    0.06
    Act Density 0.001%

    No Known Activations