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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -aut
    -0.08
     hasn
    -0.07
     Cubs
    -0.07
    .executor
    -0.07
     Bau
    -0.07
     Kosten
    -0.07
     haben
    -0.07
     neb
    -0.07
     onFocus
    -0.07
     TOP
    -0.06
    POSITIVE LOGITS
    ///↵↵
    0.08
    &)↵
    0.07
     зап
    0.07
     lời
    0.07
     villagers
    0.07
     major
    0.07
    圾
    0.07
    遇
    0.07
    🧴
    0.06
    ayment
    0.06
    Act Density 0.028%

    No Known Activations