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

    Neuronpedia

    INDEX
    Explanations

    headings and abstracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <b>
    0.53
    7
    0.53
    8
    0.49
    9
    0.48
    ur
    0.47
    0
    0.46
    st
    0.46
    n
    0.45
    cn
    0.45
    ource
    0.45
    POSITIVE LOGITS
     conflit
    0.48
    钥匙
    0.47
     पृ
    0.45
     usuario
    0.44
     équip
    0.43
     calci
    0.43
     encom
    0.42
    籙
    0.42
     vif
    0.42
    的总
    0.41
    Act Density 0.008%

    No Known Activations