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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (preg
    -0.07
     JAN
    -0.07
     बच
    -0.06
     Bet
    -0.06
    (age
    -0.06
     fury
    -0.06
    .Pro
    -0.06
    剂
    -0.06
     上
    -0.06
     pups
    -0.06
    POSITIVE LOGITS
    asca
    0.07
     matplotlib
    0.07
    нат
    0.06
    ляються
    0.06
    UIFont
    0.06
     >&
    0.06
    			↵
    0.06
    oid
    0.06
    				↵
    0.06
    uali
    0.06
    Act Density 0.014%

    No Known Activations