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

    Neuronpedia

    INDEX
    Explanations

    based on or solely upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     básicas
    0.53
    Basic
    0.51
    basic
    0.47
     basic
    0.46
     बेसिक
    0.44
     básico
    0.43
     Basic
    0.43
     базо
    0.42
    basics
    0.41
     básica
    0.41
    POSITIVE LOGITS
     off
    0.89
     solely
    0.89
     upon
    0.74
     purely
    0.66
     on
    0.64
     على
    0.63
     Sole
    0.61
     عليها
    0.61
    sole
    0.59
     darauf
    0.59
    Act Density 0.061%

    No Known Activations