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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qc
    -0.06
     WHICH
    -0.06
     ولكن
    -0.06
     QUESTION
    -0.06
    audit
    -0.06
    tokens
    -0.06
     INCLUDED
    -0.06
     Matters
    -0.06
    言い
    -0.06
    mixed
    -0.06
    POSITIVE LOGITS
    641
    0.07
     Finland
    0.07
     đông
    0.06
    .bed
    0.06
    風
    0.06
    uenta
    0.06
    Infinity
    0.06
     बढ
    0.06
     chrono
    0.06
    ulfill
    0.06
    Act Density 0.008%

    No Known Activations