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

    Neuronpedia

    INDEX
    Explanations

    message

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    θε
    -0.06
     anticipate
    -0.06
    Fill
    -0.06
     overl
    -0.06
    ást
    -0.05
    omite
    -0.05
     ettiği
    -0.05
    :_
    -0.05
    (viewModel
    -0.05
    .sy
    -0.05
    POSITIVE LOGITS
     message
    0.09
     Mage
    0.07
    DSL
    0.07
    orient
    0.07
     mensaje
    0.07
     messages
    0.07
     discrimination
    0.07
    -non
    0.07
    ]
↵
↵
    0.07
    logged
    0.07
    Act Density 0.019%

    No Known Activations