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

    Neuronpedia

    INDEX
    Explanations

    identifying list items and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असलेल्या
    0.36
    ֖
    0.36
    வர்களில்
    0.34
     addNew
    0.34
     intravenously
    0.33
     diagonally
    0.32
    急性
    0.32
     codon
    0.31
     matplotlib
    0.31
     nemmeno
    0.31
    POSITIVE LOGITS
     ,
    0.62
    ،
    0.59
    、
    0.58
     و
    0.56
     ،
    0.51
     и
    0.51
    ၊
    0.49
    ፣
    0.48
    力和
    0.47
    !,
    0.47
    Act Density 0.701%

    No Known Activations