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

    Neuronpedia

    INDEX
    Explanations

    Nonsense/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     下午
    -0.07
    alık
    -0.06
    Coverage
    -0.06
     Handlers
    -0.06
    giene
    -0.06
     '../../../../../
    -0.06
    inventory
    -0.06
    народ
    -0.06
    <lemma
    -0.05
    .setStatus
    -0.05
    POSITIVE LOGITS
    .Ag
    0.07
     onları
    0.07
     гру
    0.07
     waived
    0.07
     проводить
    0.07
     saved
    0.06
     WON
    0.06
     Unreal
    0.06
    oooooooo
    0.06
     glGet
    0.06
    Act Density 0.033%

    No Known Activations