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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .strokeStyle
    -0.07
    ccc
    -0.07
    Choose
    -0.07
    observ
    -0.07
     proc
    -0.06
     ISBN
    -0.06
     observ
    -0.06
    	vec
    -0.06
    stąpi
    -0.06
    ถ
    -0.06
    POSITIVE LOGITS
     Mayer
    0.08
     clans
    0.07
    ᴈ
    0.07
    _ENTRY
    0.07
    赞赏
    0.07
    دعم
    0.07
    Mayor
    0.06
    𝖊
    0.06
     Hera
    0.06
     Dre
    0.06
    Act Density 0.029%

    No Known Activations