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

    Neuronpedia

    INDEX
    Explanations

    say "purposes"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jedi
    -0.07
     ÜNİVERSİTESİ
    -0.07
     Oasis
    -0.06
    (klass
    -0.06
     стоит
    -0.06
    、私
    -0.06
     Incre
    -0.06
     starring
    -0.06
     chất
    -0.06
     switched
    -0.06
    POSITIVE LOGITS
    (age
    0.06
     enterprise
    0.06
    --)
    0.06
    Usage
    0.06
     diff
    0.06
    (*)
    0.06
    +/
    0.06
     Mining
    0.06
     MIME
    0.06
     اجتماعی
    0.06
    Act Density 0.144%

    No Known Activations