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

    Neuronpedia

    INDEX
    Explanations

    organizational structures

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱯ
    0.65
     fabrik
    0.64
     पोजीशन
    0.62
     fudge
    0.61
     tunnels
    0.59
     учё
    0.59
     muzik
    0.59
     tunnelling
    0.58
     ребён
    0.57
    picker
    0.56
    POSITIVE LOGITS
     Org
    0.61
     Structural
    0.58
     Catalan
    0.58
    をもって
    0.58
     electoral
    0.57
     Organizational
    0.57
     Donald
    0.57
     Instruction
    0.55
     overwhelmingly
    0.55
     Structures
    0.55
    Act Density 0.001%

    No Known Activations