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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чком
    0.59
     sheep
    0.57
    oplanes
    0.56
    ills
    0.55
    此同时
    0.55
     opposites
    0.55
    вайтесь
    0.55
     opp
    0.54
    rexham
    0.54
    findOrFail
    0.52
    POSITIVE LOGITS
    PPP
    0.56
    providers
    0.54
    CLOS
    0.52
    สมัคร
    0.52
    lever
    0.52
    ヴァン
    0.52
     atender
    0.51
    PARTY
    0.51
    Addr
    0.51
    άζ
    0.51
    Act Density 0.000%

    No Known Activations