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

    Neuronpedia

    INDEX
    Explanations

    Research/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Králové
    -0.07
    strength
    -0.06
    егор
    -0.06
    vocab
    -0.06
     Pos
    -0.06
     BOOLEAN
    -0.06
     취
    -0.06
    .Relative
    -0.06
     шп
    -0.06
     zase
    -0.06
    POSITIVE LOGITS
     factions
    0.07
    oves
    0.06
    )didReceiveMemoryWarning
    0.06
    ----------</
    0.06
    負
    0.06
    www
    0.06
     bere
    0.06
    ');</
    0.06
     increments
    0.06
    .vector
    0.06
    Act Density 0.171%

    No Known Activations