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

    Neuronpedia

    INDEX
    Explanations

    say "Patent" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Не
    -0.07
    oders
    -0.07
     QUESTION
    -0.07
    .yml
    -0.07
     lesbian
    -0.06
    sembl
    -0.06
    lesen
    -0.06
     germany
    -0.06
     embeddings
    -0.06
     ain
    -0.06
    POSITIVE LOGITS
     infring
    0.06
     counterpart
    0.06
     counterparts
    0.06
    맨
    0.06
     เท
    0.06
    .sdk
    0.06
    707
    0.06
    εδ
    0.06
     LCS
    0.06
    .ToTable
    0.06
    Act Density 0.010%

    No Known Activations