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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dell
    -0.07
     flattering
    -0.07
    riger
    -0.07
    -player
    -0.07
    $sql
    -0.06
    妇
    -0.06
     económ
    -0.06
    -like
    -0.06
     slept
    -0.06
    Foot
    -0.06
    POSITIVE LOGITS
    _RC
    0.08
     heraus
    0.07
     ^
    0.06
    spiracy
    0.06
     παρα
    0.06
    DownLatch
    0.06
     Crash
    0.06
     (!$
    0.06
    �
    0.05
     onboard
    0.05
    Act Density 0.018%

    No Known Activations