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

    Neuronpedia

    INDEX
    Explanations

    destruction and withstanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.49
     ICT
    0.47
    粘
    0.46
    OPTIONS
    0.45
     Podemos
    0.45
    Listener
    0.44
     progetti
    0.43
    陣
    0.42
     Antioxid
    0.42
     synapse
    0.42
    POSITIVE LOGITS
    𝙩
    0.49
    destruction
    0.48
    iterranean
    0.48
    었다
    0.47
     slaying
    0.47
     destroying
    0.46
    າ
    0.46
    ierten
    0.45
    withstanding
    0.44
    日上午
    0.43
    Act Density 0.005%

    No Known Activations