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

    Neuronpedia

    INDEX
    Explanations

    how things work and mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surveys
    0.92
     survey
    0.89
     विविध
    0.85
     تصمیم
    0.83
     actitudes
    0.83
    建议
    0.82
     agendas
    0.81
     atteggi
    0.81
     opiniones
    0.81
     Surveys
    0.80
    POSITIVE LOGITS
     mechanism
    2.06
     Mechanism
    1.97
    mechanism
    1.92
    Mechanism
    1.91
     механизм
    1.84
    原理
    1.67
     explanation
    1.67
     mechanisms
    1.64
     funzionamento
    1.62
     Mechanisms
    1.62
    Act Density 1.247%

    No Known Activations