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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -heading
    -0.07
     Wenger
    -0.07
    然而
    -0.06
    岁的
    -0.06
     blogger
    -0.06
    充满
    -0.06
     demands
    -0.06
    cern
    -0.06
    mob
    -0.06
    性的
    -0.06
    POSITIVE LOGITS
    ☃
    0.07
     Terra
    0.07
    區
    0.07
     Frem
    0.07
     TEM
    0.07
    짬
    0.07
     pedestal
    0.06
    _UNUSED
    0.06
    ใต
    0.06
     foreground
    0.06
    Act Density 0.035%

    No Known Activations