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

    Neuronpedia

    INDEX
    Explanations

    clauses starting with the word "after" or "before"

    oai_token-act-pair · gemini-2.0-flash

    after before

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhiêu
    -0.48
    ính
    -0.48
    rizona
    -0.46
    ització
    -0.44
    itize
    -0.44
    anmoins
    -0.44
    nskap
    -0.44
     وأن
    -0.43
     refusé
    -0.43
     därför
    -0.43
    POSITIVE LOGITS
     becoming
    0.96
     taking
    0.94
     making
    0.93
     gaining
    0.93
     helping
    0.88
     getting
    0.88
     releasing
    0.87
     managing
    0.86
     giving
    0.86
     being
    0.84
    Act Density 1.298%

    No Known Activations