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

    Neuronpedia

    INDEX
    Explanations

    newly created objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imparted
    0.40
     satisfactory
    0.37
    湁
    0.36
     descript
    0.36
    네요
    0.36
     deduct
    0.35
    孚
    0.35
     expresa
    0.35
    UNK
    0.34
    മിക
    0.34
    POSITIVE LOGITS
    0.40
     upcoming
    0.40
     scrapbook
    0.40
     लायक
    0.39
     Launch
    0.39
    iseite
    0.39
    کروچ
    0.39
    itol
    0.39
     Rad
    0.38
     chrome
    0.38
    Act Density 0.000%

    No Known Activations