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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stasy
    -0.08
     Groß
    -0.08
    佟
    -0.07
    簉
    -0.07
     tài
    -0.07
    .visitMethodInsn
    -0.06
    𝕝
    -0.06
     müd
    -0.06
    failure
    -0.06
     Australia
    -0.06
    POSITIVE LOGITS
     Session
    0.07
     revisions
    0.07
    曲
    0.07
    拼音
    0.07
    Filtered
    0.07
     Circle
    0.07
     chairs
    0.06
    Publisher
    0.06
    	unset
    0.06
    贬
    0.06
    Act Density 0.011%

    No Known Activations