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

    Neuronpedia

    INDEX
    Explanations

    Internet safety topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ፒ
    0.44
    껭
    0.44
    귄
    0.43
     arah
    0.42
     preached
    0.41
     ajoute
    0.40
     descanso
    0.40
     gelecek
    0.40
    ონი
    0.40
    राग
    0.39
    POSITIVE LOGITS
     Boolean
    0.45
     Date
    0.42
     into
    0.40
     Mapping
    0.38
     Internet
    0.38
     MEM
    0.38
     Resources
    0.38
    ृत्य
    0.37
    UDP
    0.37
    anum
    0.37
    Act Density 0.000%

    No Known Activations