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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cyst
    -0.09
     شف
    -0.08
    Make
    -0.08
    Laugh
    -0.08
     bitter
    -0.08
    Shr
    -0.07
     gemaakt
    -0.07
     વીડિયો
    -0.07
    'wina
    -0.07
    ირვ
    -0.07
    POSITIVE LOGITS
     strength
    0.10
     mạnh
    0.09
    力度
    0.09
    _strength
    0.09
     Field
    0.09
     magnitude
    0.09
     Strength
    0.08
     intensidad
    0.08
     Ambient
    0.08
     strongest
    0.08
    Act Density 0.004%

    No Known Activations