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

    Neuronpedia

    INDEX
    Explanations

    parties and operands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crystals
    0.44
    හර
    0.38
     egip
    0.37
    arla
    0.36
    Kay
    0.35
     зага
    0.35
     अल
    0.35
     agrade
    0.35
     Sunshine
    0.35
     despised
    0.35
    POSITIVE LOGITS
     operand
    1.41
     Parties
    1.32
     parties
    1.30
     operands
    1.28
    operand
    1.24
    parties
    1.16
     signatories
    1.09
    Operand
    1.08
     signatory
    1.01
     Operand
    0.98
    Act Density 0.039%

    No Known Activations