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

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الم
    -0.08
     Hal
    -0.07
     yang
    -0.07
     caul
    -0.07
    其实
    -0.07
     Its
    -0.06
     partisan
    -0.06
     şimdi
    -0.06
    )+"
    -0.06
    *****
↵
    -0.06
    POSITIVE LOGITS
     places
    0.06
     Unity
    0.06
    fontWeight
    0.06
    _pro
    0.06
    	users
    0.06
     ketogenic
    0.06
    quiz
    0.06
    ある
    0.06
    .gold
    0.06
     Ced
    0.06
    Act Density 0.002%

    No Known Activations