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

    Neuronpedia

    INDEX
    Explanations

    Limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attacks
    -0.07
     lassen
    -0.07
    velopment
    -0.06
     trừ
    -0.06
    оп
    -0.06
    /lic
    -0.06
    030
    -0.06
     vol
    -0.06
    lož
    -0.06
    Interceptor
    -0.06
    POSITIVE LOGITS
     DbType
    0.06
    8
    0.06
     Deployment
    0.06
     ‌
    0.06
    _ESCAPE
    0.06
     DNS
    0.06
     Том
    0.05
     Same
    0.05
    WordPress
    0.05
     YT
    0.05
    Act Density 0.010%

    No Known Activations