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

    Neuronpedia

    INDEX
    Explanations

    label=" or label='

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beitet
    0.51
    IZED
    0.50
    sequently
    0.50
    ldre
    0.47
     ストレ
    0.47
    nto
    0.46
    ld
    0.45
    ao
    0.45
    za
    0.45
    loir
    0.45
    POSITIVE LOGITS
     Propaganda
    0.44
     Drag
    0.44
     Dr
    0.43
     Tolkien
    0.43
     Uranium
    0.43
    必须
    0.43
     Kafka
    0.42
    劳动
    0.42
     Dependencies
    0.42
     Equip
    0.41
    Act Density 0.003%

    No Known Activations