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

    Neuronpedia

    INDEX
    Explanations

    throw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restart
    -0.07
    plorer
    -0.07
    olta
    -0.06
    -summary
    -0.06
     restarting
    -0.06
    	IL
    -0.06
    .restore
    -0.06
     conv
    -0.06
    ocyte
    -0.06
     women
    -0.06
    POSITIVE LOGITS
    [loc
    0.07
     солн
    0.07
     erste
    0.06
    teacher
    0.06
    dyž
    0.06
    Greek
    0.06
    _qp
    0.06
    	mutex
    0.06
    .search
    0.06
    -million
    0.06
    Act Density 0.003%

    No Known Activations