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

    Neuronpedia

    INDEX
    Explanations

    stable legs, framing, rigidity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lingered
    0.42
    agawa
    0.38
     lingers
    0.37
    ."),
    0.37
    anine
    0.36
     dares
    0.36
    $.)
    0.36
    ushed
    0.35
    hunter
    0.35
    inari
    0.35
    POSITIVE LOGITS
     stiff
    0.80
     rigid
    0.73
     rigidity
    0.73
     stiffness
    0.72
     Stiffness
    0.69
    rigid
    0.68
     Rigid
    0.68
     ríg
    0.67
     Rig
    0.59
     stiffer
    0.58
    Act Density 0.000%

    No Known Activations