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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iples
    -0.07
     chats
    -0.06
    .segment
    -0.06
     ambiguous
    -0.06
    =<?=$
    -0.06
     люди
    -0.06
    ��
    -0.06
    makt
    -0.06
    (Unit
    -0.06
    ‘
    -0.06
    POSITIVE LOGITS
    _cls
    0.06
    -go
    0.06
     ActionBar
    0.06
    MatrixMode
    0.06
    trib
    0.06
    aclass
    0.06
    _management
    0.06
     fc
    0.06
     useRouter
    0.06
     cereal
    0.06
    Act Density 0.003%

    No Known Activations