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

    Neuronpedia

    INDEX
    Explanations

    "ment" + Spanish suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ië
    0.55
    iéndose
    0.52
    iénd
    0.51
    ное
    0.49
    स्या
    0.48
    änen
    0.48
     decidió
    0.47
    ammlung
    0.47
    irão
    0.47
     novamente
    0.46
    POSITIVE LOGITS
    REAT
    0.48
    pof
    0.47
    き
    0.46
    endswith
    0.46
     trees
    0.46
     bottomLeft
    0.45
    ь
    0.45
     }}$,
    0.45
    leaves
    0.45
     rumours
    0.44
    Act Density 0.000%

    No Known Activations