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
     Collapse
    -0.08
     adicional
    -0.08
     Dresses
    -0.08
     Suspend
    -0.08
     Update
    -0.07
     gyr
    -0.07
     supplémentaire
    -0.07
     existente
    -0.07
     Deposit
    -0.07
     Vault
    -0.07
    POSITIVE LOGITS
     wholeheartedly
    0.09
     hars
    0.08
    Ich
    0.08
     footing
    0.08
    新的
    0.08
     permanent
    0.08
    0.08
     Buddhism
    0.08
     Richtung
    0.08
     tactics
    0.07
    Act Density 0.052%
    No Known Activations