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

    Neuronpedia

    INDEX
    Explanations

    ney

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arse
    -0.07
     Cultural
    -0.06
    icamente
    -0.06
    pires
    -0.06
    隐
    -0.06
    PropertyDescriptor
    -0.06
    番
    -0.06
    ots
    -0.06
    argar
    -0.06
    eydi
    -0.06
    POSITIVE LOGITS
    _crossentropy
    0.06
    Fant
    0.06
    -dd
    0.06
    Woman
    0.06
     phosphate
    0.06
     mythical
    0.06
    NT
    0.06
     enh
    0.06
     сер
    0.06
    	exit
    0.05
    Act Density 0.016%

    No Known Activations