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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     编辑
    -0.08
    Dess
    -0.08
     bands
    -0.08
     regels
    -0.08
     lotions
    -0.07
    -edit
    -0.07
     Sothe
    -0.07
    -ie
    -0.07
    "S
    -0.07
     Oscars
    -0.07
    POSITIVE LOGITS
     proposing
    0.11
     propuesta
    0.11
     proposée
    0.10
     proposer
    0.10
     propose
    0.09
     proposé
    0.09
     proposal
    0.09
     предлагаем
    0.09
     Proposed
    0.09
     Proposal
    0.09
    Act Density 0.016%

    No Known Activations