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

    Neuronpedia

    INDEX
    Explanations

    arguing or presenting arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     least
    0.42
    least
    0.39
     oon
    0.38
     difíciles
    0.34
     liber
    0.34
     tendencies
    0.34
     much
    0.34
     definitely
    0.34
    ゲット
    0.33
     mucho
    0.33
    POSITIVE LOGITS
     argument
    0.64
     аргу
    0.61
    argument
    0.58
     Argument
    0.52
     arguments
    0.52
    Argument
    0.52
     argumentation
    0.52
    arguments
    0.46
     якобы
    0.46
     arguing
    0.44
    Act Density 0.105%

    No Known Activations