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

    Neuronpedia

    INDEX
    Explanations

    error messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ശക്ത
    -0.09
     শক্ত
    -0.08
     പ്രത്യേക
    -0.08
     toughness
    -0.07
     PSP
    -0.07
     विशेष
    -0.07
     pantry
    -0.07
     بذلك
    -0.07
     Derr
    -0.07
     ingredient
    -0.07
    POSITIVE LOGITS
    Scripts
    0.11
     ~/
    0.10
    fuck
    0.09
     unsuccess
    0.09
    Repo
    0.08
     Scripts
    0.08
    /scripts
    0.08
    Rabbit
    0.08
     étrange
    0.08
    hluk
    0.08
    Act Density 0.008%

    No Known Activations