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

    Neuronpedia

    INDEX
    Explanations

    specifying different types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ర్
    1.22
    史上
    1.17
    ormous
    1.16
    isasi
    1.14
    ร์
    1.12
    keb
    1.11
    ेन
    1.11
    mment
    1.10
    ricted
    1.08
    觴
    1.07
    POSITIVE LOGITS
     pleasurable
    1.14
     necesidades
    1.12
    $$
    1.05
    ക്കോ
    1.05
     pleasing
    1.02
     trypsin
    1.02
    ].
    0.99
     desired
    0.99
    控件
    0.99
     pleasant
    0.97
    Act Density 0.098%

    No Known Activations