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

    Neuronpedia

    INDEX
    Explanations

    preceding the topic

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    ,
    -0.11
     hashMap
    -0.08
    עש
    -0.07
     Enum
    -0.07
    ᅵ
    -0.07
     Casey
    -0.07
     kill
    -0.07
    )\
    -0.07
    的原因
    -0.06
     język
    -0.06
    POSITIVE LOGITS
    esters
    0.08
    一致好评
    0.07
    houette
    0.07
    mus
    0.07
    sr
    0.07
    contentType
    0.07
    posit
    0.07
    در
    0.07
    (rotation
    0.06
    dropIfExists
    0.06
    Act Density 0.209%

    No Known Activations