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

    Neuronpedia

    INDEX
    Explanations

    access control, flow, IP, cost elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...\
    0.48
    !\
    0.46
     !\
    0.45
     kammam
    0.45
    !”.
    0.44
     bahwa
    0.43
     ^^
    0.43
     මෙම
    0.43
    hner
    0.43
    .’’
    0.42
    POSITIVE LOGITS
     his
    0.51
     built
    0.50
     chants
    0.50
    ብ
    0.50
    모
    0.49
     z
    0.49
     n
    0.48
     units
    0.48
    for
    0.48
     Local
    0.48
    Act Density 0.118%

    No Known Activations