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

    Neuronpedia

    INDEX
    Explanations

    Morale and confidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Default
    -0.07
     Bog
    -0.06
    ible
    -0.06
    Soon
    -0.06
     ambassador
    -0.06
    Professional
    -0.06
    _PARAMETER
    -0.06
     Excel
    -0.06
     exponential
    -0.06
    (Math
    -0.06
    POSITIVE LOGITS
    ículo
    0.07
    :l
    0.06
     msgid
    0.06
     mệnh
    0.06
     زی
    0.06
     l
    0.06
     cresc
    0.06
     messages
    0.06
    mouseleave
    0.06
     řád
    0.06
    Act Density 0.058%

    No Known Activations