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

    Neuronpedia

    INDEX
    Explanations

    AI model instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     signe
    -0.08
    _vo
    -0.08
    essione
    -0.08
    Praise
    -0.08
    anen
    -0.07
    ACP
    -0.07
    stations
    -0.07
     ভার
    -0.07
     Weitere
    -0.07
     més
    -0.07
    POSITIVE LOGITS
    र्त
    0.08
     Talking
    0.08
     resolver
    0.07
     oamen
    0.07
     mock
    0.07
    uelto
    0.07
     solve
    0.07
     speculate
    0.07
    ർത്ത
    0.07
     speculation
    0.07
    Act Density 0.000%

    No Known Activations