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

    Neuronpedia

    INDEX
    Explanations

    parasites and taxonomy

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    (group
    -0.07
    (box
    -0.07
    生素
    -0.07
     constructs
    -0.07
    segments
    -0.06
    של
    -0.06
     값
    -0.06
    substr
    -0.06
    "He
    -0.06
    本场比赛
    -0.06
    POSITIVE LOGITS
     Verb
    0.07
     Documentary
    0.07
     recipes
    0.07
     deserving
    0.07
     Housing
    0.07
    -devel
    0.07
    Ŏ
    0.07
    utivo
    0.06
     Asked
    0.06
    大棚
    0.06
    Act Density 0.053%

    No Known Activations