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

    Neuronpedia

    INDEX
    Explanations

    generations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mul
    -0.07
    ü
    -0.07
    Length
    -0.06
     fortress
    -0.06
     mogul
    -0.06
     worms
    -0.06
    _PP
    -0.06
     puck
    -0.06
    star
    -0.06
    apikey
    -0.06
    POSITIVE LOGITS
     generations
    0.14
     generation
    0.13
    -generation
    0.12
     Generation
    0.08
     世
    0.07
    (adapter
    0.07
     prostřed
    0.07
     Les
    0.07
     graphite
    0.07
    期
    0.07
    Act Density 0.007%

    No Known Activations