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

    Neuronpedia

    INDEX
    Explanations

    references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enkins
    -0.07
    ']="
    -0.07
     provoz
    -0.06
    jur
    -0.06
    Hallo
    -0.06
     Django
    -0.06
    _WITH
    -0.06
    Birth
    -0.06
     Jenkins
    -0.06
    .Go
    -0.06
    POSITIVE LOGITS
    菲
    0.07
     implies
    0.06
     implying
    0.06
     incumbent
    0.06
    \t
    0.06
    恩
    0.06
    بی
    0.06
     amusing
    0.06
     remote
    0.06
     Upper
    0.06
    Act Density 0.001%

    No Known Activations