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

    Neuronpedia

    INDEX
    Explanations

    references to the availability of data or resources in various contexts

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

    available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     success
    -0.32
     Professor
    -0.32
     MISC
    -0.31
    success
    -0.30
    folg
    -0.30
     SUCCESS
    -0.28
    ereien
    -0.27
     dirait
    -0.27
     social
    -0.27
    RefNanny
    -0.27
    POSITIVE LOGITS
    available
    0.99
     Available
    0.96
     available
    0.94
    Available
    0.94
     availability
    0.90
     Availability
    0.87
    vailable
    0.84
    availability
    0.84
     disponible
    0.84
    Availability
    0.84
    Act Density 0.118%

    No Known Activations