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

    Neuronpedia

    INDEX
    Explanations

    completing sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    common
    0.54
    ai
    0.54
    peer
    0.54
    all
    0.53
    program
    0.53
    ang
    0.52
    Peer
    0.52
    impse
    0.51
    the
    0.51
    ın
    0.50
    POSITIVE LOGITS
     MotoGP
    0.56
     🤔
    0.49
     UTM
    0.48
     isAdmin
    0.47
     UHD
    0.46
     macOS
    0.46
     Ebola
    0.46
     arrêté
    0.46
     afin
    0.45
     NVIC
    0.44
    Act Density 0.002%

    No Known Activations