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

    Neuronpedia

    INDEX
    Explanations

    Caesar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    1.94
     وهذه
    1.72
    و
    1.70
    й
    1.69
    तून
    1.63
    badges
    1.49
    म
    1.49
    ب
    1.45
    ν
    1.45
    י
    1.44
    POSITIVE LOGITS
    iduría
    1.36
    ière
    1.30
    على
    1.29
    lere
    1.26
    тому
    1.25
    нодоро
    1.25
    めの
    1.24
     stride
    1.23
     Trees
    1.23
     TreeNode
    1.23
    Act Density 0.038%

    No Known Activations