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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ploader
    -0.07
     essent
    -0.07
     analyzing
    -0.07
     funer
    -0.07
     doek
    -0.07
     pandem
    -0.07
     hype
    -0.07
    opath
    -0.07
     kämpfen
    -0.07
     voto
    -0.07
    POSITIVE LOGITS
    任选
    0.14
     arbitrary
    0.11
     demonstration
    0.11
     beisp
    0.11
     wille
    0.10
     exemple
    0.10
     arbitr
    0.10
     Choose
    0.10
     qualsevol
    0.10
     purposely
    0.10
    Act Density 0.042%

    No Known Activations