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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     astonished
    -0.07
    ARSE
    -0.07
    rear
    -0.06
     you
    -0.06
    uco
    -0.06
     USB
    -0.06
    Qualifier
    -0.06
     ".$
    -0.06
    uffix
    -0.06
     House
    -0.06
    POSITIVE LOGITS
    )))),
    0.07
     ninete
    0.06
    elix
    0.06
    porn
    0.06
     나는
    0.06
     اعتر
    0.06
     functionality
    0.06
     unmistak
    0.06
    -motion
    0.06
    stalk
    0.06
    Act Density 0.006%

    No Known Activations