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

    Neuronpedia

    INDEX
    Explanations

    <table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	make
    -0.07
    :N
    -0.07
    "N
    -0.07
     impacts
    -0.06
     ()↵
    -0.06
    .Toggle
    -0.06
     ri
    -0.06
    Si
    -0.06
     getPassword
    -0.06
    se
    -0.06
    POSITIVE LOGITS
     واب
    0.06
     CSV
    0.06
     AES
    0.06
    اهی
    0.06
     Bols
    0.06
     calam
    0.06
    akens
    0.06
    (locations
    0.06
    contracts
    0.06
     ケ
    0.06
    Act Density 0.059%

    No Known Activations