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

    Neuronpedia

    INDEX
    Explanations

    re

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     friendships
    0.93
     hook
    0.82
     friends
    0.79
     addiction
    0.78
     ljubav
    0.78
    hook
    0.77
     affiliates
    0.77
    Friends
    0.76
     friendship
    0.76
     Romance
    0.76
    POSITIVE LOGITS
    consume
    0.68
    kelijk
    0.65
    峯
    0.63
     dalej
    0.63
     respond
    0.61
     rocks
    0.61
    radar
    0.61
     consume
    0.60
     da
    0.60
    uur
    0.59
    Act Density 0.225%

    No Known Activations