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

    Neuronpedia

    INDEX
    Explanations

    road signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    煅
    -0.07
     option
    -0.07
     Islamabad
    -0.07
    纸
    -0.06
    럼
    -0.06
    硅
    -0.06
    nation
    -0.06
    娲
    -0.06
    瘦身
    -0.06
    ￬
    -0.06
    POSITIVE LOGITS
    ancode
    0.07
    \E
    0.07
     wishing
    0.07
    Queue
    0.07
    stdin
    0.07
    olicies
    0.07
    רוש
    0.06
     RFC
    0.06
    atern
    0.06
    technical
    0.06
    Act Density 0.027%

    No Known Activations