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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salt
    -0.07
    .Commands
    -0.07
     overwhelm
    -0.07
    gm
    -0.07
     싸
    -0.06
     Serg
    -0.06
    elon
    -0.06
    [layer
    -0.06
    iston
    -0.06
    İY
    -0.06
    POSITIVE LOGITS
    .cleanup
    0.07
     safari
    0.06
     kond
    0.06
    splice
    0.06
     tink
    0.06
     linh
    0.06
    charging
    0.06
    tearDown
    0.06
     поль
    0.06
    edited
    0.06
    Act Density 0.014%

    No Known Activations