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

    Neuronpedia

    INDEX
    Explanations

    less stressful or demanding tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eland
    0.42
    惦
    0.41
     interpersonal
    0.40
    asm
    0.39
     nascent
    0.38
    azie
    0.38
    atic
    0.38
     በመ
    0.37
    ions
    0.37
    aham
    0.37
    POSITIVE LOGITS
     rarely
    0.47
     deberá
    0.47
    职责
    0.47
     uniquement
    0.46
    endrá
    0.45
    φορά
    0.45
     endast
    0.44
    બે
    0.43
     only
    0.43
     devra
    0.43
    Act Density 0.003%

    No Known Activations