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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gosta
    -0.09
     pady
    -0.09
    .vars
    -0.08
     wohnen
    -0.08
     adgang
    -0.08
     strøm
    -0.08
     espere
    -0.08
     komst
    -0.08
     getline
    -0.08
     EMA
    -0.08
    POSITIVE LOGITS
    plete
    0.08
     positive
    0.08
     collaborative
    0.07
     Kent
    0.07
    etailed
    0.07
     photographic
    0.07
     positiven
    0.07
    ungeons
    0.07
     satisfies
    0.07
    insky
    0.07
    Act Density 0.000%

    No Known Activations