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

    Neuronpedia

    INDEX
    Explanations

    job position or vision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᆭ
    0.49
     bright
    0.48
    LOS
    0.48
    cribing
    0.48
     mba
    0.47
    CVE
    0.47
    ‍
    0.47
     helpful
    0.46
     homeowner
    0.46
     magnifying
    0.45
    POSITIVE LOGITS
     افس
    0.45
    在中国
    0.44
     اخیر
    0.43
     phas
    0.43
     удосто
    0.42
     ओवरटाइम
    0.42
     ஆண்க
    0.41
    য়নের
    0.41
    㚘
    0.41
     semula
    0.41
    Act Density 0.000%

    No Known Activations