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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "do"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Feel
    0.41
     Feel
    0.39
    ork
    0.39
    ток
    0.38
     있
    0.38
    Subtitle
    0.38
    orka
    0.38
     Remix
    0.38
     Revolutionary
    0.38
     Whatever
    0.37
    POSITIVE LOGITS
     श्रेणी
    0.41
    iseries
    0.38
     BH
    0.38
    猫
    0.37
     Nichols
    0.36
    olia
    0.36
    TERN
    0.35
     measured
    0.35
     bh
    0.35
    lès
    0.35
    Act Density 0.003%

    No Known Activations