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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eo
    -0.07
    ição
    -0.07
     oste
    -0.06
    öße
    -0.06
     землі
    -0.06
     puesto
    -0.06
    awa
    -0.06
     tally
    -0.06
    (child
    -0.06
     tiếp
    -0.06
    POSITIVE LOGITS
    forc
    0.07
    ((_
    0.07
    Direction
    0.07
     availability
    0.06
    /routes
    0.06
    (Map
    0.06
     drž
    0.06
     Flush
    0.06
    VersionUID
    0.06
     Action
    0.06
    Act Density 0.002%

    No Known Activations