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

    Neuronpedia

    INDEX
    Explanations

    spanning across

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Notify
    0.59
    getInfo
    0.57
    掄
    0.57
    lela
    0.56
    fda
    0.56
    Heat
    0.54
    Hear
    0.54
     Barron
    0.54
     revamp
    0.54
    Fres
    0.53
    POSITIVE LOGITS
     hovered
    0.70
     fluctu
    0.59
    不可能
    0.59
     spanned
    0.57
     अधिकांश
    0.57
     transcendent
    0.57
    marshalO
    0.57
     അവസാന
    0.57
     никогда
    0.56
     spanning
    0.55
    Act Density 0.000%

    No Known Activations