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

    Neuronpedia

    INDEX
    Explanations

    64

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recur
    -0.07
     жил
    -0.07
    _ori
    -0.06
     �
    -0.06
    allel
    -0.06
    _foot
    -0.06
    ों,
    -0.06
    .goal
    -0.06
     kat
    -0.06
     VIC
    -0.06
    POSITIVE LOGITS
    collection
    0.07
    Genesis
    0.07
     dé
    0.06
     Moves
    0.06
    essional
    0.06
     dividend
    0.06
    creator
    0.06
    .condition
    0.06
    oupper
    0.06
    ньому
    0.06
    Act Density 0.001%

    No Known Activations