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

    Neuronpedia

    INDEX
    Explanations

    analysis of genome structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ():
    0.21
    {
    0.19
    <unused2197>
    0.18
    📄
    0.17
    <unused2130>
    0.17
    📌
    0.17
     bazı
    0.17
    <unused2169>
    0.17
    에는
    0.17
     públic
    0.16
    POSITIVE LOGITS
     activism
    0.22
     analysis
    0.22
     defiance
    0.21
     reass
    0.20
     Analysis
    0.20
     scrutiny
    0.19
     manipulation
    0.19
     elasticity
    0.19
     complacency
    0.19
     transparence
    0.19
    Act Density 0.977%

    No Known Activations