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

    Neuronpedia

    INDEX
    Explanations

    rigorous or rigid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    垣
    0.39
    ége
    0.37
     Sponge
    0.36
    sponge
    0.36
    είο
    0.36
     emf
    0.36
     strongly
    0.36
    רית
    0.35
     defi
    0.35
    ixon
    0.34
    POSITIVE LOGITS
    Rig
    0.79
     rig
    0.71
    Gig
    0.68
    rig
    0.68
    Ig
    0.66
     ig
    0.65
     Rig
    0.65
    RIG
    0.64
     Tig
    0.64
    ig
    0.63
    Act Density 0.010%

    No Known Activations