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

    Neuronpedia

    INDEX
    Explanations

    FF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lbl
    -0.06
    folder
    -0.06
     grounds
    -0.06
    Son
    -0.06
     scratches
    -0.06
    c
    -0.06
     publi
    -0.06
    ､:
    -0.06
    colour
    -0.06
    Calc
    -0.06
    POSITIVE LOGITS
     Args
    0.07
     뭐
    0.07
     trình
    0.06
     nghiệm
    0.06
     poate
    0.06
    ちは
    0.06
     обязательно
    0.06
     eventData
    0.06
     xây
    0.06
     згад
    0.06
    Act Density 0.000%

    No Known Activations