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

    Neuronpedia

    INDEX
    Explanations

    Technical writing/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endid
    -0.07
    -being
    -0.06
     Tester
    -0.06
    ocytes
    -0.06
    pants
    -0.06
     Sat
    -0.06
     كتاب
    -0.06
    ニメ
    -0.06
     �
    -0.06
    Cad
    -0.06
    POSITIVE LOGITS
    сім
    0.08
     verst
    0.07
     رسم
    0.07
    _float
    0.07
    =tf
    0.07
    รอบ
    0.07
    áo
    0.07
     eliminating
    0.07
     send
    0.07
     tw
    0.07
    Act Density 0.000%

    No Known Activations