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

    Neuronpedia

    INDEX
    Explanations

    interest is calculated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nécessaires
    0.54
     durée
    0.50
     lavish
    0.47
     nécessaire
    0.47
     needed
    0.47
     danger
    0.47
     文字
    0.47
     minhas
    0.46
     sire
    0.46
     cot
    0.46
    POSITIVE LOGITS
    Nano
    0.56
    Host
    0.55
    Gaming
    0.54
    nano
    0.50
    Monitoring
    0.50
    Basic
    0.48
    Crypt
    0.48
    Testing
    0.47
    nant
    0.47
    Real
    0.46
    Act Density 0.000%

    No Known Activations