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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dirty
    -0.07
     Memories
    -0.06
    sqlite
    -0.06
     delt
    -0.06
     LOVE
    -0.06
     Kling
    -0.06
    autiful
    -0.06
     love
    -0.06
    Java
    -0.06
     black
    -0.06
    POSITIVE LOGITS
    .manual
    0.07
    <translation
    0.07
    úp
    0.06
     домов
    0.06
     Worth
    0.06
    historic
    0.06
    _meter
    0.06
    ocurrency
    0.06
    (service
    0.06
    icester
    0.06
    Act Density 0.036%

    No Known Activations