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
     pork
    -0.07
    (Element
    -0.07
     routine
    -0.06
    ké
    -0.06
    vrier
    -0.06
     데이터
    -0.06
    plugin
    -0.06
    	array
    -0.06
     Feld
    -0.06
    college
    -0.06
    POSITIVE LOGITS
    abyrinth
    0.07
     Spiral
    0.06
     zách
    0.06
    \Domain
    0.06
     �
    0.06
     adım
    0.06
     chevy
    0.06
     يم
    0.06
     existential
    0.06
     indir
    0.06
    Act Density 0.421%

    No Known Activations