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

    Neuronpedia

    INDEX
    Explanations

    Adhering to guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    자료
    -0.06
     शक
    -0.06
    mem
    -0.06
    bond
    -0.05
    .degree
    -0.05
    оке
    -0.05
    destruct
    -0.05
    ิโ
    -0.05
     microscopy
    -0.05
     Georgian
    -0.05
    POSITIVE LOGITS
     ".$
    0.08
     confirming
    0.07
    .menu
    0.07
     supporting
    0.06
    *=*=
    0.06
     withdrawals
    0.06
     Faul
    0.06
     exemplary
    0.06
     indie
    0.06
     duel
    0.06
    Act Density 0.013%

    No Known Activations