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

    Neuronpedia

    INDEX
    Explanations

    bells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tools
    -0.73
    tools
    -0.71
    NASA
    -0.71
     NASA
    -0.62
    GEBURTSDATUM
    -0.61
    flags
    -0.60
    Flags
    -0.60
    ness
    -0.60
    исленность
    -0.59
    s
    -0.57
    POSITIVE LOGITS
     lumineuse
    0.57
     estimés
    0.53
     destiny
    0.48
    wpi
    0.47
     batches
    0.47
    ٰ
    0.46
    دهم
    0.46
     economically
    0.45
     ApiResponse
    0.45
    VITA
    0.45
    Act Density 0.718%

    No Known Activations