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

    Neuronpedia

    INDEX
    Explanations

    Addresses and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     output
    -0.07
     sons
    -0.07
    iro
    -0.06
     bố
    -0.06
    _probability
    -0.06
    ocha
    -0.06
    isans
    -0.06
    สว
    -0.06
    war
    -0.06
    .CASCADE
    -0.06
    POSITIVE LOGITS
     resett
    0.06
     GR
    0.06
     Carroll
    0.06
     Heg
    0.06
     Cree
    0.06
    .SpringBootApplication
    0.06
    اگر
    0.06
     ^=
    0.06
     crypt
    0.06
     Hearth
    0.06
    Act Density 0.007%

    No Known Activations