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

    Neuronpedia

    INDEX
    Explanations

    waits for, modifies, grown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தரும்
    0.39
    licas
    0.37
    ❚
    0.36
    ₁(
    0.35
     distinctive
    0.35
     असे
    0.35
    ené
    0.34
    ေး
    0.34
    ничный
    0.34
    تعليم
    0.33
    POSITIVE LOGITS
    渲
    0.40
    Inflater
    0.40
     seconded
    0.40
    惪
    0.39
     Ashby
    0.37
    औ
    0.36
     sop
    0.36
    νονται
    0.36
     ondul
    0.36
    Mens
    0.35
    Act Density 0.000%

    No Known Activations