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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vulner
    -0.09
    -0.08
     Offshore
    -0.08
     Garden
    -0.08
     Humor
    -0.07
     Outs
    -0.07
     clima
    -0.07
     FMI
    -0.07
     Cem
    -0.07
     Editorial
    -0.07
    POSITIVE LOGITS
     onchange
    0.12
     veranderingen
    0.11
     perubahan
    0.11
     changements
    0.10
    改变
    0.10
     changes
    0.10
    Changing
    0.10
     wijzigingen
    0.10
    变化
    0.10
     changement
    0.10
    Act Density 0.004%
    No Known Activations