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

    Neuronpedia

    INDEX
    Explanations

    LIMIT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attrs
    -0.07
    itat
    -0.06
    ordering
    -0.06
     burger
    -0.06
     元
    -0.06
    )item
    -0.06
    Whats
    -0.06
    .CG
    -0.06
    oded
    -0.06
    study
    -0.06
    POSITIVE LOGITS
     guarantees
    0.07
     LIMIT
    0.07
    Dave
    0.07
     Antworten
    0.07
    (er
    0.06
     rowIndex
    0.06
     Instances
    0.06
    (width
    0.06
     Require
    0.06
     ventured
    0.06
    Act Density 0.004%

    No Known Activations