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

    Neuronpedia

    INDEX
    Explanations

    adding text and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     液
    0.66
    Technische
    0.66
    Technical
    0.63
     값을
    0.62
    Voltage
    0.62
    Long
    0.62
     感
    0.61
    Sen
    0.61
    Mutex
    0.61
    curvature
    0.60
    POSITIVE LOGITS
     proponents
    1.03
     postmodern
    1.00
     educators
    0.99
     preachers
    0.97
     theologians
    0.94
     professors
    0.94
     pornography
    0.93
     pastors
    0.92
     hostel
    0.92
     scandals
    0.91
    Act Density 0.000%

    No Known Activations