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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Object
    -0.07
     Tv
    -0.07
     RIGHTS
    -0.07
     iface
    -0.07
     parameters
    -0.06
    ormap
    -0.06
     Stern
    -0.06
     circuits
    -0.06
    _CART
    -0.06
     FG
    -0.06
    POSITIVE LOGITS
     합니다
    0.06
    muştur
    0.06
    арь
    0.06
     passport
    0.06
     lyon
    0.06
    _targets
    0.06
     Cub
    0.06
     EXPORT
    0.06
    stairs
    0.06
    ılmış
    0.06
    Act Density 0.004%

    No Known Activations