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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𬘫
    -0.07
    _allocate
    -0.07
    Transformer
    -0.06
     quên
    -0.06
    .osgi
    -0.06
    memset
    -0.06
    卮
    -0.06
    专注于
    -0.06
     Friday
    -0.06
     AutoMapper
    -0.06
    POSITIVE LOGITS
    機構
    0.08
    lik
    0.08
    ACING
    0.07
     manip
    0.07
    otation
    0.07
    帮助
    0.07
    _song
    0.07
    想法
    0.07
    _activ
    0.07
    ental
    0.07
    Act Density 0.006%

    No Known Activations