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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crew
    -0.07
     budget
    -0.07
    College
    -0.06
    'image
    -0.06
    umo
    -0.06
    ogie
    -0.06
    sound
    -0.06
     resonate
    -0.06
    ait
    -0.06
    ше
    -0.06
    POSITIVE LOGITS
    อค
    0.07
    Cpp
    0.07
    쪽
    0.07
    コン
    0.07
    روش
    0.06
    -zero
    0.06
     dismissing
    0.06
    .toDouble
    0.06
    akistan
    0.06
    �
    0.06
    Act Density 0.022%

    No Known Activations