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

    Neuronpedia

    INDEX
    Explanations

    alternative opportunity risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विवेकानंद
    0.37
    突
    0.37
    增
    0.36
    マラ
    0.36
     Locals
    0.36
     Ferté
    0.36
     increments
    0.36
     Fertil
    0.35
     residentes
    0.35
    洗
    0.35
    POSITIVE LOGITS
     альтерна
    0.64
     alternative
    0.63
    alternative
    0.59
    opportunity
    0.54
     opportunity
    0.54
     alternate
    0.53
     Alternative
    0.53
    Alternative
    0.53
     alternativas
    0.52
     alternativ
    0.52
    Act Density 0.002%

    No Known Activations