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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نصف
    -0.08
    	Collection
    -0.07
    java
    -0.07
    膝
    -0.07
     ple
    -0.07
     wee
    -0.07
    _as
    -0.07
     Art
    -0.07
     person
    -0.06
    video
    -0.06
    POSITIVE LOGITS
    的动力
    0.09
    groups
    0.08
    ượt
    0.08
    irá
    0.07
     growers
    0.07
     nhắn
    0.07
    /helpers
    0.07
    stype
    0.07
    _PARENT
    0.07
     Hundreds
    0.07
    Act Density 0.208%

    No Known Activations