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

    Neuronpedia

    INDEX
    Explanations

    distance from the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    एसएल
    0.36
    assers
    0.36
     iza
    0.35
    衚
    0.34
    Networks
    0.34
    媛
    0.34
    Title
    0.34
    を守
    0.33
    捗
    0.33
    Pv
    0.33
    POSITIVE LOGITS
     benöt
    0.43
     ritrov
    0.43
    任何人
    0.43
     Meghna
    0.41
    距离
    0.41
     เมื่อ
    0.40
     beiden
    0.40
     Chamb
    0.40
    ពេល
    0.40
     Pointer
    0.40
    Act Density 0.003%

    No Known Activations