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

    Neuronpedia

    INDEX
    Explanations

    healing and cleanliness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     хими
    0.40
     şeyler
    0.40
     തന്നെയാണ്
    0.38
    !("{:
    0.37
     размере
    0.37
     proteine
    0.37
     hips
    0.36
     optimised
    0.36
     लेस
    0.36
     почита
    0.36
    POSITIVE LOGITS
    ぐるみ
    0.44
    obal
    0.39
    ▢
    0.38
     vinyl
    0.37
    ઝા
    0.37
    sibling
    0.37
    凖
    0.37
    Defining
    0.36
    soap
    0.36
     पुढ
    0.36
    Act Density 0.000%

    No Known Activations