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

    Neuronpedia

    INDEX
    Explanations

    Code or technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cant
    -0.06
     كار
    -0.06
     รอง
    -0.06
     Floral
    -0.06
     thủy
    -0.06
     Franken
    -0.06
     fiat
    -0.06
     kazanç
    -0.05
     corres
    -0.05
    朱
    -0.05
    POSITIVE LOGITS
    -source
    0.07
    -з
    0.07
     freaking
    0.06
    Med
    0.06
     disposing
    0.06
    ETERS
    0.06
     stalo
    0.06
    arian
    0.06
    arking
    0.06
    policy
    0.06
    Act Density 0.000%

    No Known Activations