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

    Neuronpedia

    INDEX
    Explanations

    names, likely Isaac

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lite
    -0.08
     car
    -0.08
     Milan
    -0.08
    65
    -0.08
     stad
    -0.07
    art
    -0.07
     network
    -0.07
    Công
    -0.07
     page
    -0.07
    680
    -0.07
    POSITIVE LOGITS
     Daniel
    0.08
     Jonathan
    0.08
     Abraham
    0.08
     Rachel
    0.07
     Gabriel
    0.07
     Aaron
    0.07
     Seth
    0.07
     Benjamin
    0.07
     Levi
    0.07
     Isaac
    0.07
    Act Density 0.061%

    No Known Activations