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

    Neuronpedia

    INDEX
    Explanations

    -tree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    なん
    -0.07
    _es
    -0.07
    ps
    -0.07
    Canadian
    -0.07
     strconv
    -0.07
     реша
    -0.07
    äs
    -0.07
    큽
    -0.07
     겁
    -0.07
    _conn
    -0.07
    POSITIVE LOGITS
     armies
    0.07
    .Dialog
    0.07
     witty
    0.07
     introduces
    0.07
    .Persistence
    0.06
    互利
    0.06
     velocities
    0.06
     remembered
    0.06
     Indonesia
    0.06
     moot
    0.06
    Act Density 0.000%

    No Known Activations