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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    名校
    -0.07
    骄
    -0.07
    (depth
    -0.07
    .physics
    -0.06
    =index
    -0.06
    .getC
    -0.06
     המד
    -0.06
    🌚
    -0.06
     formatDate
    -0.06
     virtue
    -0.06
    POSITIVE LOGITS
    systems
    0.08
     restrained
    0.07
    出手
    0.07
     learnt
    0.07
     blunt
    0.07
     reports
    0.07
    谇
    0.07
     TB
    0.07
     PST
    0.06
    SB
    0.06
    Act Density 0.002%

    No Known Activations