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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iale
    -0.07
     Conse
    -0.07
     xấu
    -0.06
    iga
    -0.06
    oro
    -0.06
    ôn
    -0.06
     Omaha
    -0.06
    istas
    -0.06
    aku
    -0.06
    ames
    -0.06
    POSITIVE LOGITS
     Apple
    0.07
     eject
    0.06
     Westbrook
    0.06
    structures
    0.06
    <(),
    0.06
    ्ध
    0.06
    	while
    0.06
     gastro
    0.06
     gadget
    0.06
    -dir
    0.06
    Act Density 0.010%

    No Known Activations