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

    Neuronpedia

    INDEX
    Explanations

    coherent text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objs
    -0.07
     "",
    -0.06
    _mgmt
    -0.06
     ль
    -0.06
     oluyor
    -0.06
     Esp
    -0.06
    кол
    -0.06
    _merged
    -0.06
    speech
    -0.06
    .DataGridView
    -0.06
    POSITIVE LOGITS
     teaching
    0.07
    ity
    0.06
     distancing
    0.06
     headlines
    0.06
     hlas
    0.06
    阶段
    0.06
     Teaching
    0.06
    _span
    0.06
    umbs
    0.06
     scarce
    0.06
    Act Density 0.000%

    No Known Activations