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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roth
    -0.06
     اغ
    -0.06
    .Players
    -0.06
    ्ल
    -0.06
    .sales
    -0.06
     enumerated
    -0.06
    ','=',
    -0.06
     kayı
    -0.06
     ’
    -0.06
    、三
    -0.06
    POSITIVE LOGITS
    �
    0.08
     �
    0.08
     waypoint
    0.08
    ip
    0.08
    /messages
    0.07
     Pit
    0.07
     creatively
    0.07
    ancements
    0.07
     mesmer
    0.07
    quartered
    0.07
    Act Density 0.004%

    No Known Activations