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

    Neuronpedia

    INDEX
    Explanations

    -step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tacoma
    -0.07
    “A
    -0.06
     hidden
    -0.06
    _department
    -0.06
     не
    -0.06
    riangle
    -0.06
     southern
    -0.06
     přeb
    -0.06
     offices
    -0.06
     DataView
    -0.06
    POSITIVE LOGITS
     tokens
    0.07
    ас
    0.07
     smith
    0.06
     示例
    0.06
    -bre
    0.06
    ABCDE
    0.06
    paced
    0.06
    ッド
    0.06
     OUR
    0.06
     anlamına
    0.06
    Act Density 0.011%

    No Known Activations