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

    Neuronpedia

    INDEX
    Explanations

    problem solved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elaborate
    -0.07
    ']↵↵
    -0.07
    !!↵↵
    -0.07
    igma
    -0.07
    任何一个
    -0.07
     ROC
    -0.07
     turbo
    -0.06
    高速增长
    -0.06
    !!↵
    -0.06
    ogonal
    -0.06
    POSITIVE LOGITS
    Starting
    0.07
     getUsername
    0.07
     chose
    0.06
    廠
    0.06
     sounding
    0.06
    WithName
    0.06
    샜
    0.06
    kernel
    0.06
     works
    0.06
     wirk
    0.06
    Act Density 0.129%

    No Known Activations