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

    Neuronpedia

    INDEX
    Explanations

    text editor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     செயல்படுத்த
    0.47
     courtyard
    0.38
    ឈ្ម
    0.38
     BGPS
    0.37
    Breakfast
    0.37
     ठेव
    0.37
     ঘূর্ণ
    0.37
    rchen
    0.36
    Housing
    0.36
    plement
    0.36
    POSITIVE LOGITS
     editing
    1.80
    编辑
    1.67
     편집
    1.67
     editor
    1.66
     editors
    1.63
     edit
    1.59
    編輯
    1.55
     редакти
    1.55
     Editing
    1.54
     edits
    1.51
    Act Density 0.026%

    No Known Activations