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

    Neuronpedia

    INDEX
    Explanations

    navigate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Materials
    -0.06
    .GroupLayout
    -0.06
     Simpsons
    -0.06
    -three
    -0.06
     supporters
    -0.06
     improvement
    -0.06
     Sixth
    -0.06
    �
    -0.06
     засобів
    -0.06
     sixth
    -0.06
    POSITIVE LOGITS
     navigate
    0.08
     navigating
    0.07
     застосування
    0.07
     کند
    0.07
     블
    0.07
    нт
    0.06
    ，或
    0.06
    _KEYS
    0.06
     caveat
    0.06
     sorunu
    0.06
    Act Density 0.010%

    No Known Activations