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

    Neuronpedia

    INDEX
    Explanations

    syntax related to data structures and algorithms

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

    "idx:" appearing in code-like sequences

    np_acts-logits-general · gemini-2.0-flash

    best index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")(
    -0.56
    ].(
    -0.54
     commissioning
    -0.52
    àm
    -0.52
     elic
    -0.51
     rosemary
    -0.51
    CppMethod
    -0.50
    ]()
    -0.50
    httphttps
    -0.49
    Circa
    -0.49
    POSITIVE LOGITS
     candidats
    0.71
     voisins
    0.65
     pair
    0.65
     candidate
    0.65
     next
    0.63
     candidates
    0.59
     candidat
    0.58
     temporales
    0.58
     hessen
    0.57
    candidate
    0.57
    Act Density 0.967%

    No Known Activations