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

    Neuronpedia

    INDEX
    Explanations

    short

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Babe
    -0.07
    webpack
    -0.07
     Planet
    -0.07
    bia
    -0.07
     flag
    -0.07
    upa
    -0.07
     vibes
    -0.06
     Ain
    -0.06
     vida
    -0.06
    โปรแกรม
    -0.06
    POSITIVE LOGITS
     short
    0.21
     Short
    0.18
    Short
    0.17
    short
    0.15
     SHORT
    0.13
    SHORT
    0.12
    -short
    0.12
    _short
    0.11
     shorter
    0.11
    	short
    0.11
    Act Density 0.030%

    No Known Activations