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

    Neuronpedia

    INDEX
    Explanations

    email closings and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    1.34
    4
    1.26
     is
    1.16
    ai
    1.03
    f
    1.00
    r
    1.00
    er
    0.96
    "
    0.96
    v
    0.94
    ja
    0.93
    POSITIVE LOGITS
    ל
    1.77
    י
    1.36
    یر
    1.16
    یک
    1.14
    נ
    1.08
    おそらく
    1.07
    ב
    1.05
    ע
    1.04
    なっている
    1.03
    یت
    1.00
    Act Density 0.203%

    No Known Activations