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

    Neuronpedia

    INDEX
    Explanations

    App:: new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.28
    dent
    0.28
     пят
    0.27
     fortnight
    0.27
    LEC
    0.26
    ent
    0.26
    gran
    0.26
    authors
    0.26
    auk
    0.25
    removeChild
    0.25
    POSITIVE LOGITS
     القيام
    0.27
     التواصل
    0.27
    㸵
    0.27
    राणिक
    0.26
     Così
    0.26
    畲
    0.26
     Seeing
    0.26
     ইন্দু
    0.26
     对于
    0.26
     බෙ
    0.26
    Act Density 0.000%

    No Known Activations