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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MG
    -0.07
    Writing
    -0.07
     Maid
    -0.07
     元
    -0.06
     situación
    -0.06
     Також
    -0.06
     confrontation
    -0.06
    Length
    -0.06
    /dialog
    -0.06
     blaze
    -0.06
    POSITIVE LOGITS
    stoff
    0.08
    歲
    0.06
    ipated
    0.06
    .case
    0.05
    .lab
    0.05
    eron
    0.05
    .website
    0.05
    /customer
    0.05
    ithmetic
    0.05
    /graph
    0.05
    Act Density 0.096%

    No Known Activations