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

    Neuronpedia

    INDEX
    Explanations

    Greek symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kaspersky
    0.77
     Joomla
    0.74
     Paytm
    0.73
     SharePoint
    0.73
     QuickBooks
    0.72
     Skyscanner
    0.70
     Pensacola
    0.68
     PUBG
    0.67
     HIPAA
    0.66
     PayPal
    0.66
    POSITIVE LOGITS
    tilde
    0.90
    widehat
    0.89
    theta
    0.83
    varepsilon
    0.82
    sigma
    0.81
    Gamma
    0.80
    epsilon
    0.80
    infty
    0.78
    Theta
    0.77
    Phi
    0.77
    Act Density 0.016%

    No Known Activations