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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    𓃢
    -0.08
     recruit
    -0.07
    許多
    -0.07
    ords
    -0.07
    سود
    -0.06
    人数
    -0.06
    IENT
    -0.06
    	Route
    -0.06
    乎
    -0.06
     perfil
    -0.06
    POSITIVE LOGITS
    嚣
    0.07
     GHz
    0.07
     haze
    0.07
    膈
    0.07
    athlete
    0.07
     sırasında
    0.07
     DISCLAIMS
    0.06
     televised
    0.06
    _ce
    0.06
    裱
    0.06
    Act Density 0.039%

    No Known Activations