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

    Neuronpedia

    INDEX
    Explanations

    snaps, clasps, and locking mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tightly
    0.57
     Oils
    0.39
    tight
    0.39
     सहायता
    0.39
    crm
    0.38
    augment
    0.38
    anding
    0.37
     tight
    0.37
     වැඩ
    0.37
     erc
    0.37
    POSITIVE LOGITS
     snap
    0.89
     snaps
    0.88
     Snap
    0.80
     mechanism
    0.79
     locking
    0.78
    Snap
    0.77
     clasp
    0.76
     Locking
    0.75
     mecanismo
    0.74
     snapping
    0.74
    Act Density 0.020%

    No Known Activations