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

    Neuronpedia

    INDEX
    Explanations

    aim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Accessories
    -0.08
     äußer
    -0.08
     Accessories
    -0.08
     hil
    -0.07
     resort
    -0.07
     eject
    -0.07
     functools
    -0.07
     destroy
    -0.07
     travel
    -0.07
     coll
    -0.07
    POSITIVE LOGITS
     striving
    0.12
     desirable
    0.12
    _threshold
    0.12
     Threshold
    0.12
     behalen
    0.12
    threshold
    0.11
     seuil
    0.11
    _THRESHOLD
    0.11
    Threshold
    0.11
     thresholds
    0.11
    Act Density 0.045%

    No Known Activations