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

    Neuronpedia

    INDEX
    Explanations

    been, did

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    European
    -0.07
     European
    -0.07
    .controls
    -0.06
    слід
    -0.06
    ології
    -0.06
    interpret
    -0.05
    ión
    -0.05
    .Dataset
    -0.05
     tendr
    -0.05
     Edit
    -0.05
    POSITIVE LOGITS
     migrations
    0.07
    _mp
    0.07
     Tud
    0.07
    ปร
    0.07
    }`}>↵
    0.07
    (cards
    0.06
     porch
    0.06
    PREFIX
    0.06
    321
    0.06
    009
    0.06
    Act Density 0.266%

    No Known Activations