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

    Neuronpedia

    INDEX
    Explanations

    code, symbols, and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eyes
    0.45
     beyond
    0.45
     rec
    0.44
     re
    0.44
    ,
    0.43
     complete
    0.43
     O
    0.43
     land
    0.41
     inter
    0.41
     pea
    0.41
    POSITIVE LOGITS
    код
    0.57
     Fmat
    0.56
    zynarod
    0.56
    <unused212>
    0.54
    ableConcept
    0.53
    ስቃሴ
    0.53
    }^{\#
    0.52
    ስማ
    0.52
    <unused691>
    0.52
    <unused618>
    0.51
    Act Density 0.000%

    No Known Activations