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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    18
    -0.07
     contrace
    -0.07
    irse
    -0.07
     限
    -0.07
     sym
    -0.06
     NotImplementedException
    -0.06
     เข
    -0.06
    (lon
    -0.06
     eighteen
    -0.06
     kein
    -0.06
    POSITIVE LOGITS
     helping
    0.10
     helps
    0.10
     helped
    0.10
     help
    0.10
     Helping
    0.09
     Help
    0.08
     helpful
    0.08
    liked
    0.07
     serving
    0.07
    هل
    0.07
    Act Density 0.094%

    No Known Activations