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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     stappen
    -0.07
     Tiene
    -0.07
    feren
    -0.07
     herr
    -0.07
     concentrates
    -0.07
    levant
    -0.07
    criter
    -0.07
     flies
    -0.07
    lookup
    -0.07
    POSITIVE LOGITS
     עצמי
    0.09
     संप
    0.08
     என
    0.08
     hingegen
    0.08
     ஆனால்
    0.08
    .self
    0.07
     Dyson
    0.07
    ////↵
    0.07
     //--------------------------------
    0.07
     அல
    0.07
    Act Density 0.027%
    No Known Activations