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

    Neuronpedia

    INDEX
    Explanations

    fluid retention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     put
    0.42
     Kemudian
    0.42
    activating
    0.42
     punishable
    0.42
     penalty
    0.41
     follicles
    0.41
     courtyard
    0.41
     lease
    0.41
     allowable
    0.41
    ptives
    0.41
    POSITIVE LOGITS
    玦
    0.50
    socketState
    0.41
    Myst
    0.40
    वस्तु
    0.40
    去看
    0.39
     aus
    0.39
    нце
    0.38
    রিতে
    0.38
     الاخر
    0.38
    Firebase
    0.38
    Act Density 23.845%

    No Known Activations