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

    Neuronpedia

    INDEX
    Explanations

    questions and "¿"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungkinkan
    0.83
     pooling
    0.74
    }@
    0.74
     sociis
    0.74
     hydrophilic
    0.73
     categorization
    0.72
     informatics
    0.72
     foaming
    0.71
     negative
    0.70
     impatience
    0.69
    POSITIVE LOGITS
     Finds
    0.92
    вели
    0.84
     बैठ
    0.83
     หลัง
    0.83
    ချက်
    0.83
     Rid
    0.82
    糸
    0.81
     कोले
    0.80
    Après
    0.80
     letzte
    0.80
    Act Density 0.001%

    No Known Activations