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

    Neuronpedia

    INDEX
    Explanations

    positive comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rowth
    -0.07
    中小学
    -0.07
    /admin
    -0.07
    identally
    -0.06
     interrupted
    -0.06
     cluster
    -0.06
    渗透
    -0.06
    濋
    -0.06
    udent
    -0.06
    acle
    -0.06
    POSITIVE LOGITS
     billed
    0.08
     unus
    0.07
     ana
    0.07
    相关负责
    0.07
    堐
    0.07
    踦
    0.07
     gồ
    0.07
    耥
    0.07
    国土资源
    0.07
    ynamo
    0.06
    Act Density 0.050%

    No Known Activations