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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lin
    -0.06
    (/
    -0.06
    huge
    -0.06
     cops
    -0.06
     trouble
    -0.06
     Hp
    -0.06
     Dire
    -0.06
    .testing
    -0.06
     StringTokenizer
    -0.06
     gang
    -0.06
    POSITIVE LOGITS
    nger
    0.07
     offerings
    0.07
    στημα
    0.07
    neighbors
    0.06
    .domain
    0.06
     Driving
    0.06
    ichern
    0.06
    SENSOR
    0.06
    .asset
    0.06
     느�
    0.06
    Act Density 0.019%

    No Known Activations