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

    Neuronpedia

    INDEX
    Explanations

    union

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fir
    -0.07
    .mods
    -0.07
    Difficulty
    -0.06
    adě
    -0.06
    produto
    -0.06
    燕
    -0.06
    ственное
    -0.06
    (P
    -0.06
    Equivalent
    -0.06
    ná
    -0.06
    POSITIVE LOGITS
     Uruguay
    0.06
    Variables
    0.06
     Alan
    0.06
     ALLOW
    0.06
     IPS
    0.06
     spiritual
    0.06
    /shop
    0.06
    GN
    0.06
    Tube
    0.06
     configure
    0.06
    Act Density 0.001%

    No Known Activations