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

    Neuronpedia

    INDEX
    Explanations

    regex patterns that handle alphanumeric characters, spaces, and symbols

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

    special characters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.61
     informée
    -0.59
    RenderAtEndOf
    -0.55
    didSet
    -0.55
     témoig
    -0.53
     IndexPath
    -0.53
    MLLoader
    -0.53
    
    -0.53
     GenerationType
    -0.53
    FieldBuilder
    -0.51
    POSITIVE LOGITS
     characters
    0.40
    Drag
    0.36
    NegativeButton
    0.35
     particles
    0.35
     mixtures
    0.35
    æder
    0.33
     TypeError
    0.33
     bedo
    0.32
     soorten
    0.32
     especially
    0.32
    Act Density 0.020%

    No Known Activations