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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deference
    0.65
     desperation
    0.64
    かん
    0.64
     Sosa
    0.61
     oddly
    0.61
    vDash
    0.60
     overthrow
    0.60
    }}.
    0.58
     হঠাৎ
    0.58
    ანა
    0.57
    POSITIVE LOGITS
    Festival
    1.12
     festival
    1.11
     initiative
    1.10
     événement
    1.10
     Veranstaltung
    1.08
     initiatives
    1.08
     Festival
    1.07
     etkinlik
    1.06
     eventos
    1.05
     Initiatives
    1.04
    Act Density 0.067%

    No Known Activations