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

    Neuronpedia

    INDEX
    Explanations

    terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🥁
    -0.08
    emotion
    -0.07
     sak
    -0.07
    옜
    -0.07
     suffer
    -0.07
    درك
    -0.07
     mish
    -0.07
    .dark
    -0.07
    כה
    -0.06
    _ALARM
    -0.06
    POSITIVE LOGITS
     moda
    0.08
     ordered
    0.07
    准入
    0.07
    退回
    0.07
     boundaries
    0.07
     pedigree
    0.07
    _fd
    0.07
     unit
    0.07
     fullest
    0.07
    _CF
    0.06
    Act Density 0.005%

    No Known Activations