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

    Neuronpedia

    INDEX
    Explanations

    symbols and syntax elements commonly used in programming or data formats

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

    structured text and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.64
     otomatig
    -0.57
    andExpect
    -0.56
     noDo
    -0.56
    Autoritní
    -0.55
    complexContent
    -0.54
    SourceChecksum
    -0.53
    addGroup
    -0.52
     snippetHide
    -0.50
    getJSONArray
    -0.49
    POSITIVE LOGITS
    SBATCH
    0.39
     contigo
    0.37
    مصادر
    0.36
    StackNavigator
    0.35
    Navigator
    0.33
     arent
    0.32
    PhysRevLett
    0.31
     HttpNotFound
    0.31
    CodedInputStream
    0.31
     onOptions
    0.30
    Act Density 0.177%

    No Known Activations