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

    Neuronpedia

    INDEX
    Explanations

    menu, categories, property, ai, wander

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ferr
    0.40
    yles
    0.39
     ({
    0.37
    sser
    0.36
    0.36
     use
    0.36
     ।”
    0.36
     tri
    0.36
     :{
    0.35
    ☁
    0.35
    POSITIVE LOGITS
     sección
    0.43
    强
    0.43
    сун
    0.43
    团
    0.42
    ினை
    0.42
     violación
    0.42
    店铺
    0.42
    悳
    0.42
    琪
    0.41
    ສ່ວນ
    0.41
    Act Density 0.001%

    No Known Activations