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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cas
    -0.07
     cljs
    -0.07
    感情
    -0.06
    郃
    -0.06
    跨越
    -0.06
    Coding
    -0.06
    なんと
    -0.06
     inspected
    -0.06
    ción
    -0.06
     crosses
    -0.06
    POSITIVE LOGITS
    .flow
    0.07
    GUID
    0.07
     toilet
    0.07
     Wend
    0.07
    .Pro
    0.07
    شرع
    0.07
     primary
    0.07
    _variable
    0.07
     SEP
    0.07
    שור
    0.07
    Act Density 0.002%

    No Known Activations