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

    Neuronpedia

    INDEX
    Explanations

    dimensional arrays or vectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presidential
    0.59
     sulit
    0.58
    িয়া
    0.55
     aldı
    0.55
     hims
    0.54
     exs
    0.52
     Presidential
    0.51
     ক্ষেপণাস্ত্র
    0.51
    ська
    0.50
    𝒇
    0.50
    POSITIVE LOGITS
    ]">
    0.55
    et
    0.52
    or
    0.51
    uma
    0.49
    ah
    0.48
    vec
    0.48
    ich
    0.48
    CU
    0.47
    ik
    0.47
    C
    0.47
    Act Density 0.000%

    No Known Activations