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

    Neuronpedia

    INDEX
    Explanations

    varied text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     fours
    -0.06
     �
    -0.06
     tránh
    -0.06
     tamb
    -0.06
    folios
    -0.06
     themed
    -0.06
    .setup
    -0.06
    uale
    -0.06
    Curso
    -0.06
    POSITIVE LOGITS
    طح
    0.07
     taps
    0.06
     phận
    0.06
    Vm
    0.06
    (balance
    0.06
    ぇ
    0.06
     diminishing
    0.06
    emme
    0.06
    цієн
    0.06
    /up
    0.06
    Act Density 0.001%

    No Known Activations