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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cl
    -0.08
     ello
    -0.08
    _pkg
    -0.07
     Protocol
    -0.07
     ReactDOM
    -0.07
    cala
    -0.07
    slot
    -0.07
    Так
    -0.06
    _service
    -0.06
     stable
    -0.06
    POSITIVE LOGITS
    %d
    0.07
    олнитель
    0.06
     Intelli
    0.06
    \Repositories
    0.06
    /fs
    0.06
    /options
    0.06
     пре
    0.05
     Cummings
    0.05
     �
    0.05
    ogle
    0.05
    Act Density 0.004%

    No Known Activations