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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	args
    -0.07
     sold
    -0.07
    'H
    -0.07
     Betty
    -0.06
    f
    -0.06
     KeyValuePair
    -0.06
    vero
    -0.06
     coined
    -0.06
    etzt
    -0.06
     Мне
    -0.06
    POSITIVE LOGITS
     Deborah
    0.08
     сум
    0.07
    	actual
    0.07
    _fac
    0.07
    /Core
    0.07
    .Pop
    0.07
    Extern
    0.06
     السل
    0.06
    Num
    0.06
    Manual
    0.06
    Act Density 0.016%

    No Known Activations