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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fulton
    -0.06
     Pai
    -0.06
     donner
    -0.06
    -China
    -0.06
    베
    -0.06
     sexuality
    -0.06
     muht
    -0.06
     Ten
    -0.06
    $category
    -0.06
     juven
    -0.06
    POSITIVE LOGITS
    teří
    0.07
     headphones
    0.07
    IsValid
    0.07
     at
    0.06
     attracted
    0.06
     Anita
    0.06
     foreach
    0.06
     sadece
    0.06
    ('').
    0.06
     між
    0.06
    Act Density 0.000%

    No Known Activations