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

    Neuronpedia

    INDEX
    Explanations

    assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     travelers
    -0.08
     Updating
    -0.07
     빌
    -0.07
    TRANSFER
    -0.07
    Disney
    -0.07
     Kings
    -0.06
     Silicone
    -0.06
     nad
    -0.06
     Columbus
    -0.06
    .react
    -0.06
    POSITIVE LOGITS
     assistance
    0.06
    handles
    0.06
    itty
    0.06
    -dist
    0.06
    ouchers
    0.06
    mouseup
    0.06
     supernatural
    0.06
    Enemies
    0.06
    plaintext
    0.06
    (.)
    0.06
    Act Density 0.012%

    No Known Activations