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

    Neuronpedia

    INDEX
    Explanations

    tam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     +↵
    -0.07
    timestamps
    -0.07
    日报记者
    -0.07
    _vm
    -0.07
    喙
    -0.07
    _Integer
    -0.06
     Forums
    -0.06
    samp
    -0.06
    noticed
    -0.06
    שנתי
    -0.06
    POSITIVE LOGITS
    '],$_
    0.08
    nęła
    0.07
    쯩
    0.07
     playlist
    0.07
    穿上
    0.07
    ,set
    0.07
     aplic
    0.06
    的眼神
    0.06
    ḣ
    0.06
     undercut
    0.06
    Act Density 0.158%

    No Known Activations