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

    Neuronpedia

    INDEX
    Explanations

    attachment

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Swanson
    0.70
    淼
    0.59
    कांत
    0.58
    āv
    0.57
     Dieter
    0.57
    missione
    0.57
     રૂપ
    0.57
     Hayward
    0.57
     Riddle
    0.56
     coolness
    0.56
    POSITIVE LOGITS
     attachment
    2.51
     Attachment
    2.28
     attach
    2.22
     attachments
    2.20
     attaching
    2.18
    Attachment
    2.17
     attaches
    2.15
     attached
    2.15
    attachment
    2.10
     Attach
    2.04
    Act Density 0.332%

    No Known Activations