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

    Neuronpedia

    INDEX
    Explanations

    the principal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PRODUCTS
    0.39
    ジム
    0.38
    为例
    0.37
    Slot
    0.37
    kiye
    0.37
     Enzym
    0.37
    adik
    0.36
     SLOT
    0.35
     Slot
    0.35
     všet
    0.35
    POSITIVE LOGITS
     principal
    1.25
    Principal
    1.16
    principal
    1.13
     Principal
    1.13
     principle
    0.97
    PRINC
    0.97
     принци
    0.94
     principals
    0.94
     PRINC
    0.94
     princip
    0.93
    Act Density 0.002%

    No Known Activations