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

    Neuronpedia

    INDEX
    Explanations

    principal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wow
    -0.07
    eme
    -0.07
    _message
    -0.07
     Vote
    -0.07
    033
    -0.07
     aftermarket
    -0.07
    (ob
    -0.06
    keterangan
    -0.06
    438
    -0.06
    쓰
    -0.06
    POSITIVE LOGITS
     principal
    0.14
     Principal
    0.11
    Principal
    0.11
     principals
    0.10
     tranquil
    0.10
    �
    0.09
     princip
    0.08
     principally
    0.08
    raj
    0.08
    یل
    0.08
    Act Density 0.008%

    No Known Activations