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

    Neuronpedia

    INDEX
    Explanations

    terms indicating suitability or compatibility with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    suitable for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Altri
    -0.31
     Trasp
    -0.31
     totul
    -0.30
     transparence
    -0.30
    Externe
    -0.30
    nanoTime
    -0.29
     historiques
    -0.29
     droom
    -0.28
     saken
    -0.28
    ↵
    -0.27
    POSITIVE LOGITS
     suitable
    1.23
    Suitable
    1.20
    suitable
    1.19
     Suitable
    1.19
    uitable
    0.94
     appropriate
    0.92
    Appropriate
    0.86
    appropriate
    0.85
     Appropriate
    0.84
    適合
    0.81
    Act Density 0.008%

    No Known Activations