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

    Neuronpedia

    INDEX
    Explanations

    commemorate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     signed
    -0.06
    goal
    -0.06
    hotmail
    -0.06
    してい
    -0.06
    OTOS
    -0.06
     Sq
    -0.06
    *pow
    -0.06
    lucent
    -0.06
     Lies
    -0.06
     intents
    -0.06
    POSITIVE LOGITS
     Kh
    0.07
     azalt
    0.06
    idge
    0.06
    ADDR
    0.06
     Sing
    0.06
     Implement
    0.06
     parsing
    0.06
    matrix
    0.06
     Denn
    0.06
    ANDLE
    0.06
    Act Density 0.000%

    No Known Activations