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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the manner or context in which something is presented or described

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

    mechanism or perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.92
    iotensin
    -0.69
    providedIn
    -0.69
    AnimationsModule
    -0.68
    Xna
    -0.67
    SBATCH
    -0.60
    IUrlHelper
    -0.59
     Infórmanos
    -0.58
     AssemblyCompany
    -0.57
     AssemblyProduct
    -0.57
    POSITIVE LOGITS
     viewpoint
    0.65
     whereby
    0.65
     twofold
    0.64
     viewpoints
    0.55
     standpoint
    0.55
     threefold
    0.50
     commonplace
    0.46
     timeframe
    0.45
     noteworthy
    0.45
     safeguard
    0.44
    Act Density 0.011%

    No Known Activations