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

    Neuronpedia

    INDEX
    Explanations

    Car engine performance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chants
    -0.07
     "?"
    -0.06
    artifact
    -0.06
     demande
    -0.06
     Fleming
    -0.06
    robot
    -0.06
     เร
    -0.06
    needed
    -0.06
    Windows
    -0.06
    toLowerCase
    -0.06
    POSITIVE LOGITS
     necess
    0.07
    /ac
    0.06
     transition
    0.06
     silenced
    0.06
     Elect
    0.06
     кос
    0.06
     verschill
    0.06
    UIAlert
    0.06
     Marco
    0.06
     Paolo
    0.06
    Act Density 0.012%

    No Known Activations