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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UNIX
    -0.09
     million
    -0.08
     billion
    -0.08
     avaliar
    -0.08
     informatique
    -0.08
     Unix
    -0.08
    .observable
    -0.08
     ವಿವಿಧ
    -0.08
     millions
    -0.07
     предостав
    -0.07
    POSITIVE LOGITS
     symmetrical
    0.09
     Tatsache
    0.09
     triangles
    0.08
    _RAD
    0.08
    lemma
    0.08
    Lemma
    0.08
     때문이다
    0.08
     washer
    0.08
     symmetric
    0.08
     bouch
    0.08
    Act Density 0.038%

    No Known Activations