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

    Neuronpedia

    INDEX
    Explanations

    hyphens/parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    科学院
    -0.07
    erías
    -0.07
     shaders
    -0.07
     ANT
    -0.07
     ఇక
    -0.07
    igarh
    -0.07
     doctrines
    -0.07
     agendas
    -0.07
    如今
    -0.07
    ishing
    -0.07
    POSITIVE LOGITS
     raise
    0.09
    _raise
    0.09
     означает
    0.09
     exclaimed
    0.08
     obnox
    0.08
    Raise
    0.08
    raise
    0.08
    сний
    0.08
     umz
    0.08
     raising
    0.08
    Act Density 0.012%

    No Known Activations