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

    Neuronpedia

    INDEX
    Explanations

    descriptive follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logra
    0.49
     traducir
    0.45
    apag
    0.44
     lexic
    0.44
     europ
    0.43
     produt
    0.43
     trasport
    0.43
     traer
    0.42
     tind
    0.42
     mex
    0.42
    POSITIVE LOGITS
     on
    0.45
    ר
    0.45
     რომელიც
    0.44
     خم
    0.44
    }\|
    0.43
     emphasized
    0.43
    リカ
    0.43
     prejudices
    0.43
     ashamed
    0.42
    ኮ
    0.42
    Act Density 0.000%

    No Known Activations