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

    Neuronpedia

    INDEX
    Explanations

    understanding negative situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proffered
    0.42
    awaited
    0.41
     gladly
    0.39
    лега
    0.39
     Eater
    0.39
    styling
    0.38
    achtree
    0.37
     hatten
    0.36
    ≋
    0.36
    탓
    0.36
    POSITIVE LOGITS
     waste
    0.40
    Waste
    0.39
     Waste
    0.38
     affect
    0.38
    goo
    0.37
     Alps
    0.36
    waste
    0.36
     excessive
    0.35
     এখানে
    0.35
     болезни
    0.35
    Act Density 0.000%

    No Known Activations