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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (provider
    -0.06
    　ｌ
    -0.06
     CommandLine
    -0.06
    Recipe
    -0.06
     Lâm
    -0.06
    boom
    -0.06
    ์โ
    -0.06
     zero
    -0.06
    Jos
    -0.06
     ARISING
    -0.06
    POSITIVE LOGITS
     sos
    0.07
    -Americ
    0.06
    )__
    0.06
     delights
    0.06
     Rodney
    0.06
    Sdk
    0.06
    _FB
    0.06
    _unpack
    0.06
     misconduct
    0.06
     Next
    0.06
    Act Density 0.000%

    No Known Activations