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

    Neuronpedia

    INDEX
    Explanations

    naval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traps
    -0.07
    je
    -0.07
    OUNDS
    -0.07
     Masters
    -0.06
     Mb
    -0.06
    arts
    -0.06
    -controls
    -0.06
     Ko
    -0.06
     Evropy
    -0.06
    avorites
    -0.06
    POSITIVE LOGITS
    ++)
↵
    0.07
     gratuitement
    0.06
     حدود
    0.06
     hassle
    0.06
    (us
    0.06
     интер
    0.06
    awy
    0.06
     League
    0.06
    EMAIL
    0.06
    _PHOTO
    0.06
    Act Density 0.008%

    No Known Activations