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

    Neuronpedia

    INDEX
    Explanations

    explaining technical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    0.62
    that
    0.46
     it
    0.46
    alia
    0.46
     caja
    0.46
     ((
    0.45
    yect
    0.44
     electrostatic
    0.44
     indeed
    0.43
    ore
    0.43
    POSITIVE LOGITS
     підпри
    0.52
     pocas
    0.50
    ἲ
    0.46
    𝘂
    0.46
     elevados
    0.46
     এছাড়া
    0.46
    𒌓
    0.45
    胝
    0.44
    मैं
    0.44
    خری
    0.44
    Act Density 0.000%

    No Known Activations