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

    Neuronpedia

    INDEX
    Explanations

    document snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    COME
    -0.07
     Exist
    -0.07
     lvl
    -0.06
     vegetables
    -0.06
    vé
    -0.06
    来了
    -0.06
     Yah
    -0.06
     μέσα
    -0.06
     undercut
    -0.06
    .broadcast
    -0.06
    POSITIVE LOGITS
    eos
    0.07
    conda
    0.06
     disappointment
    0.06
     aest
    0.06
     neutr
    0.06
    ��
    0.06
     normally
    0.06
    .Assembly
    0.06
    なお
    0.06
    -target
    0.06
    Act Density 0.059%

    No Known Activations