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

    Neuronpedia

    INDEX
    Explanations

    )-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Neptune
    -0.07
     里
    -0.06
    GORITH
    -0.06
     congest
    -0.06
    uffled
    -0.06
    ints
    -0.06
    <K
    -0.06
    霍
    -0.05
    박
    -0.05
    _PI
    -0.05
    POSITIVE LOGITS
    	unset
    0.07
    響
    0.07
     ################################################################
    0.07
    撃
    0.07
    �체
    0.07
     disillusion
    0.06
    ':[
    0.06
    _scr
    0.06
     rib
    0.06
    getMock
    0.06
    Act Density 0.000%

    No Known Activations