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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     בשנת
    0.55
    <unused75>
    0.47
    <unused27>
    0.47
    erta
    0.46
     неза
    0.46
    ---------------+
    0.45
    ildiği
    0.45
    <unused29>
    0.45
     esigen
    0.44
     lucrat
    0.44
    POSITIVE LOGITS
     Applications
    0.52
    Applications
    0.48
    ET
    0.47
    Meteor
    0.47
     applications
    0.46
    ل
    0.46
     Instruments
    0.45
     Operational
    0.45
     Memories
    0.45
     Stations
    0.45
    Act Density 0.000%

    No Known Activations