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

    Neuronpedia

    INDEX
    Explanations

    rat experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    КА
    -0.08
     диза
    -0.06
    ANDLE
    -0.06
    ASA
    -0.06
     HEAD
    -0.06
     IDC
    -0.06
     PHONE
    -0.06
     getOrder
    -0.06
    .onViewCreated
    -0.06
    kům
    -0.06
    POSITIVE LOGITS
     προσ
    0.07
    .geometry
    0.07
    �
    0.07
     }}"></
    0.07
     соответ
    0.06
     wyn
    0.06
     Giov
    0.06
     함
    0.06
    _nt
    0.06
    ’elle
    0.06
    Act Density 0.375%

    No Known Activations