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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ducible
    -0.07
     igen
    -0.07
    xia
    -0.06
     '#
    -0.06
    pdb
    -0.06
     Disable
    -0.06
    -nine
    -0.06
    극
    -0.06
    TTY
    -0.06
     reprodu
    -0.06
    POSITIVE LOGITS
     Açık
    0.06
     capacit
    0.06
    strings
    0.06
     держ
    0.06
    ิทยา
    0.06
    арів
    0.06
    (Vec
    0.06
    ],[-
    0.06
    abbreviation
    0.06
    θα
    0.06
    Act Density 0.166%

    No Known Activations