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

    Neuronpedia

    INDEX
    Explanations

    existing or previous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Holding
    0.41
     life
    0.41
    দান
    0.39
     Confirm
    0.39
     holding
    0.38
     scrubbing
    0.38
     Life
    0.38
     information
    0.36
     hummingbird
    0.36
    holding
    0.35
    POSITIVE LOGITS
    ॰ऍ
    0.48
     originales
    0.47
    前回
    0.47
     기존
    0.46
     اضافہ
    0.46
    既存
    0.46
     precedenti
    0.45
     previos
    0.45
    原有
    0.45
     précédentes
    0.45
    Act Density 0.000%

    No Known Activations