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

    Neuronpedia

    INDEX
    Explanations

    Software

    np_max-act · gemini-2.0-flash

    instances of software-related terms and concepts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Queens
    -0.07
     attractions
    -0.06
     Creek
    -0.06
    	pt
    -0.06
     Town
    -0.06
     Walk
    -0.06
     Peek
    -0.06
     partition
    -0.06
     accent
    -0.06
     вертик
    -0.06
    POSITIVE LOGITS
     Software
    0.14
     software
    0.13
    Software
    0.12
    ware
    0.10
    /software
    0.10
    software
    0.09
    Ware
    0.09
     SOFTWARE
    0.09
    oftware
    0.08
     Steve
    0.08
    Act Density 0.032%

    No Known Activations