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

    Neuronpedia

    INDEX
    Explanations

    systems security course name constitutes connected Binding devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     regulations
    -0.77
     penger
    -0.71
     саду
    -0.71
    тном
    -0.70
    crypted
    -0.70
    謎
    -0.65
     scholars
    -0.65
     admirable
    -0.65
    LastModified
    -0.65
     soldiers
    -0.64
    POSITIVE LOGITS
     Bann
    0.91
     anecd
    0.87
    Connor
    0.87
     enclave
    0.86
     ATO
    0.86
    ISSE
    0.86
     Obsidian
    0.85
     bandoulière
    0.84
     принадлежа
    0.84
    NST
    0.82
    Act Density 0.020%

    No Known Activations