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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VA
    -0.07
     asserted
    -0.07
    vester
    -0.07
    andidates
    -0.06
     Burma
    -0.06
     realizar
    -0.06
     Beginners
    -0.06
     teens
    -0.06
    	connect
    -0.06
    .cwd
    -0.06
    POSITIVE LOGITS
     flashy
    0.07
    軟
    0.06
    .toUpperCase
    0.06
    accordion
    0.06
     جای
    0.06
    bye
    0.06
    ikki
    0.06
     hurd
    0.06
    \">
    0.06
     hairy
    0.06
    Act Density 0.014%

    No Known Activations