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

    Neuronpedia

    INDEX
    Explanations

    specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Different
    0.77
    sizeof
    0.77
    Types
    0.74
    nummer
    0.74
    𝗁
    0.73
    several
    0.72
     разных
    0.72
    parametrize
    0.72
    ijkl
    0.71
    வித
    0.70
    POSITIVE LOGITS
     extravaganza
    1.30
     extraordinaire
    1.18
     beauties
    1.03
     behem
    1.02
     mentality
    0.99
     counterparts
    0.99
     enthusiasts
    0.96
     equivalents
    0.96
     shenanigans
    0.96
    ers
    0.94
    Act Density 0.580%

    No Known Activations