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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bloom
    -0.08
    Serializable
    -0.08
    (flow
    -0.07
     communion
    -0.07
     ips
    -0.07
     harb
    -0.07
    sert
    -0.07
    ียง
    -0.07
    CHAR
    -0.07
     edible
    -0.07
    POSITIVE LOGITS
    Input
    0.08
    מפקד
    0.07
    𝖌
    0.07
    ൻ
    0.07
    有待
    0.07
     Shake
    0.07
     rez
    0.07
     Disco
    0.07
    主页
    0.06
     Pic
    0.06
    Act Density 0.006%

    No Known Activations