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

    Neuronpedia

    INDEX
    Explanations

    pup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     первый
    -0.07
    _Check
    -0.06
    力的
    -0.06
    ,$
    -0.06
     contradictions
    -0.06
    守
    -0.06
    ords
    -0.06
     contradict
    -0.06
    433
    -0.06
    _heads
    -0.06
    POSITIVE LOGITS
    unden
    0.07
    /admin
    0.07
    opic
    0.07
     projectId
    0.07
     pup
    0.07
     Consent
    0.07
     harass
    0.06
    document
    0.06
    Performed
    0.06
     alumni
    0.06
    Act Density 0.002%

    No Known Activations