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

    Neuronpedia

    INDEX
    Explanations

    hop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    recht
    -0.56
    teau
    -0.54
    ITZER
    -0.51
    abar
    -0.50
    Attrs
    -0.49
    Batis
    -0.48
    lims
    -0.48
    PLIC
    -0.48
    աստ
    -0.48
    lips
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.68
    Tracce
    0.57
     Paglinawan
    0.52
    +#+#
    0.52
     moaning
    0.50
     生命周期
    0.49
    thargy
    0.47
     beeswax
    0.47
     dorada
    0.47
     Orrell
    0.46
    Act Density 0.054%

    No Known Activations