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

    Neuronpedia

    INDEX
    Explanations

    TV show characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imageName
    -0.07
     vessel
    -0.07
     μετα
    -0.07
    ливих
    -0.06
     Bali
    -0.06
     zoek
    -0.06
     Suzuki
    -0.06
    복지
    -0.06
    boost
    -0.06
    68
    -0.06
    POSITIVE LOGITS
     Л
    0.08
     dobr
    0.06
    ="{
    0.06
    isclosed
    0.06
     transcend
    0.06
    ิด
    0.06
    _PER
    0.06
    (Thread
    0.06
    arily
    0.06
    >{$
    0.06
    Act Density 0.025%

    No Known Activations