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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     út
    -0.06
     علاوه
    -0.06
    çı
    -0.06
     curses
    -0.06
     dominance
    -0.06
     mari
    -0.06
     risks
    -0.06
     nutshell
    -0.06
    ht
    -0.06
    Suc
    -0.06
    POSITIVE LOGITS
    Conference
    0.07
    _ALL
    0.06
    (im
    0.06
    ange
    0.06
     kern
    0.06
    {};↵
    0.06
    -door
    0.06
    [current
    0.06
    svm
    0.06
     INTERN
    0.06
    Act Density 0.061%

    No Known Activations