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

    Neuronpedia

    INDEX
    Explanations

    forward/backward slashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    size
    -0.08
     формування
    -0.07
     fit
    -0.07
     part
    -0.07
     getModel
    -0.06
    =add
    -0.06
     teenagers
    -0.06
     pageTitle
    -0.06
     theaters
    -0.06
     levels
    -0.06
    POSITIVE LOGITS
    .↵↵
    0.06
     ビ
    0.06
     simplify
    0.06
    operand
    0.06
     hast
    0.06
     em
    0.06
    wingConstants
    0.05
    	elem
    0.05
    ----↵↵
    0.05
    uggestions
    0.05
    Act Density 0.037%

    No Known Activations