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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debe
    -0.07
    Reload
    -0.07
    NETWORK
    -0.07
    INESS
    -0.07
     FIRE
    -0.06
     XL
    -0.06
    particles
    -0.06
    Collision
    -0.06
     IDX
    -0.06
     nội
    -0.06
    POSITIVE LOGITS
    .readyState
    0.07
     drawbacks
    0.06
     highly
    0.06
     bible
    0.06
     #(
    0.06
     Suppose
    0.06
     lick
    0.06
    lém
    0.06
    (policy
    0.06
     sam
    0.06
    Act Density 0.002%

    No Known Activations