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

    Neuronpedia

    INDEX
    Explanations

    Terminal commands and configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     принцип
    -0.08
     softly
    -0.08
     conces
    -0.07
     SIGN
    -0.07
     виб
    -0.07
     Admission
    -0.07
     reimb
    -0.07
     Insurance
    -0.07
     Recommend
    -0.07
     багато
    -0.07
    POSITIVE LOGITS
    asque
    0.09
     fidél
    0.08
    accur
    0.08
    orpion
    0.08
    ier
    0.08
    ingana
    0.08
    ipped
    0.07
     fidèle
    0.07
     arrib
    0.07
    	transform
    0.07
    Act Density 0.001%

    No Known Activations