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
    Backend
    -0.06
    nop
    -0.06
     hawk
    -0.06
     Hwy
    -0.06
     TOKEN
    -0.06
     preset
    -0.06
    $r
    -0.06
    ώρα
    -0.06
    DEN
    -0.06
     headquartered
    -0.06
    POSITIVE LOGITS
    نام
    0.07
     kInstruction
    0.07
     натураль
    0.07
    ering
    0.06
    HostName
    0.06
    辞
    0.06
    aining
    0.06
    лов
    0.06
    ocrats
    0.06
     Barbar
    0.06
    Act Density 0.020%

    No Known Activations