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

    Neuronpedia

    INDEX
    Explanations

    miles and ounces units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (#
    0.77
     solicita
    0.72
     (+
    0.69
     coprime
    0.68
    शान
    0.68
    🖒
    0.68
     deleterious
    0.68
     학습
    0.67
    ຜະລ
    0.66
     (`
    0.66
    POSITIVE LOGITS
    Americans
    0.74
     equivalently
    0.69
     aproximadamente
    0.68
     traducción
    0.66
     คูณ
    0.65
    Bloomberg
    0.65
     estadounidenses
    0.63
     Bloomberg
    0.63
    rounded
    0.62
    Equ
    0.61
    Act Density 0.027%

    No Known Activations