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

    Neuronpedia

    INDEX
    Explanations

    Lord delivered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SerializeField
    0.44
    ме
    0.43
     Rxb
    0.42
     waahanga
    0.41
    Prés
    0.39
    вом
    0.39
    Governance
    0.38
    вій
    0.37
    Philos
    0.37
    бы
    0.36
    POSITIVE LOGITS
    ण्याचे
    0.45
     जितने
    0.42
     sangat
    0.39
     Pot
    0.38
     যতটা
    0.37
    ☜
    0.37
    ebi
    0.36
    ajari
    0.36
    insky
    0.36
    imą
    0.36
    Act Density 0.004%

    No Known Activations