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

    Neuronpedia

    INDEX
    Explanations

    _Service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weaknesses
    -0.07
    Render
    -0.07
     السعود
    -0.06
    addin
    -0.06
    'er
    -0.06
     пош
    -0.06
     consid
    -0.06
    Bar
    -0.06
     modest
    -0.06
    .Ribbon
    -0.06
    POSITIVE LOGITS
    RELATED
    0.08
    _damage
    0.07
    .feed
    0.06
     города
    0.06
     DID
    0.06
     STACK
    0.06
    (;
    0.06
    .Sequential
    0.06
     domestically
    0.06
    .Alignment
    0.06
    Act Density 0.001%

    No Known Activations