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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    背景
    -0.07
    Heart
    -0.06
    ume
    -0.06
     dubious
    -0.06
     canvas
    -0.06
     Tales
    -0.06
     STEM
    -0.06
     Bars
    -0.06
    .RequestBody
    -0.06
    .Short
    -0.06
    POSITIVE LOGITS
    .in
    0.06
    ‌شد
    0.06
     pol
    0.06
    De
    0.06
    called
    0.06
    )</
    0.06
    ̃
    0.06
     rank
    0.06
    โป
    0.06
     symp
    0.06
    Act Density 0.009%

    No Known Activations