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

    Neuronpedia

    INDEX
    Explanations

    Code/uncommon characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caves
    -0.08
    DOUBLE
    -0.07
     doktor
    -0.07
    DATA
    -0.07
    ｊ
    -0.06
    Hal
    -0.06
     bd
    -0.06
     recur
    -0.06
    ktop
    -0.06
    構
    -0.06
    POSITIVE LOGITS
    вает
    0.06
    сию
    0.06
     núi
    0.06
    (getContext
    0.06
     виды
    0.06
     reflexivity
    0.05
    uestas
    0.05
    .PathVariable
    0.05
     нарез
    0.05
    단체
    0.05
    Act Density 0.150%

    No Known Activations