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

    Neuronpedia

    INDEX
    Explanations

    -ing suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    castle
    -0.07
     セ
    -0.07
    ـ
    -0.06
     Також
    -0.06
    Alias
    -0.06
    -letter
    -0.06
     Arabs
    -0.06
     Elite
    -0.06
     technolog
    -0.06
    entication
    -0.06
    POSITIVE LOGITS
     Loki
    0.07
     direct
    0.07
    DY
    0.06
    илась
    0.06
    (AF
    0.06
    API
    0.06
    sono
    0.06
    şk
    0.06
     hoops
    0.06
     destined
    0.06
    Act Density 0.002%

    No Known Activations