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

    Neuronpedia

    INDEX
    Explanations

    amplification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    structor
    0.41
    Elizabeth
    0.40
     конку
    0.38
    सबुक
    0.37
    burne
    0.36
    ப்பழ
    0.36
    माया
    0.36
    bage
    0.36
     sacking
    0.36
    脱
    0.36
    POSITIVE LOGITS
     amplification
    3.88
     ampl
    3.75
     Ampl
    3.64
     amplify
    3.64
    Ampl
    3.61
     amplifying
    3.59
     amplified
    3.52
    ampl
    3.47
     amplifier
    3.39
     amplifiers
    3.30
    Act Density 0.025%

    No Known Activations