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

    Neuronpedia

    INDEX
    Explanations

    League/Super

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illegal
    -0.08
     REG
    -0.07
     bloc
    -0.07
     Mean
    -0.07
    (slice
    -0.07
    .DATE
    -0.06
    .Left
    -0.06
    �
    -0.06
     TOK
    -0.06
     tạp
    -0.06
    POSITIVE LOGITS
    (net
    0.09
    👵
    0.07
     decay
    0.07
     presidency
    0.07
     Way
    0.07
    .github
    0.07
    decay
    0.07
     UIFont
    0.07
    lığa
    0.06
    indy
    0.06
    Act Density 0.013%

    No Known Activations