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

    Neuronpedia

    INDEX
    Explanations

    put/place something on/in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    2.08
    <bos>
    2.08
    dove
    1.84
     mere
    1.78
    लिये
    1.73
    കര
    1.72
     Gerais
    1.72
    ीडी
    1.68
     मना
    1.65
    ième
    1.65
    POSITIVE LOGITS
     onus
    2.60
    ेंसिल
    2.48
     squarely
    2.22
    ক
    2.10
     розта
    2.07
     avanzada
    2.07
    cido
    2.01
    cU
    1.98
    RAJ
    1.92
    <td>
    1.89
    Act Density 0.037%

    No Known Activations