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

    Neuronpedia

    INDEX
    Explanations

    not tagged, a table

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    紳
    0.45
    ಬ್ಬಿಣ
    0.45
     analogues
    0.44
     良
    0.44
    ണ്ഡി
    0.43
     ऑ
    0.43
    書店
    0.43
    戾
    0.43
     சமீ
    0.43
     Акысыз
    0.43
    POSITIVE LOGITS
    string
    0.52
    ed
    0.51
    n
    0.48
     string
    0.47
    strings
    0.46
    la
    0.46
    ↵↵
    0.45
    igue
    0.45
    lo
    0.45
    ied
    0.45
    Act Density 30.452%

    No Known Activations