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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    像
    -0.07
     ↵		↵
    -0.07
     jl
    -0.07
     Beacon
    -0.07
     transport
    -0.06
    东京
    -0.06
     Cases
    -0.06
    عن
    -0.06
     RD
    -0.06
    ften
    -0.06
    POSITIVE LOGITS
    Vals
    0.08
    ♭
    0.08
    Drupal
    0.07
    conscious
    0.07
    服务能力
    0.07
    罟
    0.07
    𬶍
    0.07
    Ṧ
    0.07
     WHETHER
    0.07
    ensity
    0.07
    Act Density 0.000%

    No Known Activations