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

    Neuronpedia

    INDEX
    Explanations

    a followed by descriptive noun or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notion
    0.89
     situation
    0.82
     scenario
    0.80
     aspect
    0.78
     endearing
    0.74
     enriching
    0.74
     démarche
    0.68
     aspects
    0.67
     adorable
    0.66
     notions
    0.66
    POSITIVE LOGITS
    Bit
    0.69
    py
    0.68
    Volatility
    0.66
     Bit
    0.66
     References
    0.66
    মূ
    0.66
    bit
    0.66
    References
    0.65
    Referencias
    0.65
    Good
    0.64
    Act Density 0.320%

    No Known Activations