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

    Neuronpedia

    INDEX
    Explanations

    scientific and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific terms related to materials, substances, or interfaces in research contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     between
    -1.20
     между
    -1.13
     między
    -0.90
     zwischen
    -0.90
    mpi
    -0.86
    🤮
    -0.85
     між
    -0.82
    DECLARATION
    -0.81
     dintre
    -0.81
    between
    -0.81
    POSITIVE LOGITS
    Other
    0.88
     or
    0.85
    sistency
    0.85
     altavoz
    0.76
    Daughter
    0.76
    lasia
    0.74
    Timber
    0.73
    相手
    0.73
     penetration
    0.72
    開発
    0.72
    Act Density 0.138%

    No Known Activations