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

    Neuronpedia

    INDEX
    Explanations

    black center, modulo operation, Switch Reflow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Curly
    0.42
     pegawai
    0.40
    Donnell
    0.40
    Wallace
    0.39
    來看一下
    0.39
     HashTable
    0.38
    conver
    0.38
    wall
    0.38
    decorative
    0.38
     humeral
    0.38
    POSITIVE LOGITS
     Empowerment
    0.39
     своим
    0.39
     Regeneration
    0.38
    钒
    0.37
     heartbreaking
    0.37
    ěj
    0.37
    ljena
    0.37
    řen
    0.36
     Gemüse
    0.36
    延伸
    0.36
    Act Density 0.001%

    No Known Activations