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

    Neuronpedia

    INDEX
    Explanations

    Code endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ist
    -0.08
     können
    -0.07
     stellen
    -0.07
     wür
    -0.07
     involved
    -0.07
    计
    -0.07
     Eine
    -0.07
     won
    -0.07
     forward
    -0.07
     Ray
    -0.07
    POSITIVE LOGITS
    🕝
    0.08
    facebook
    0.08
    .books
    0.08
     Birth
    0.07
    .rpc
    0.07
     cider
    0.07
    mploy
    0.07
     mongodb
    0.07
     mimetype
    0.07
    tí
    0.07
    Act Density 0.058%

    No Known Activations