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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pard
    -0.06
    .placeholder
    -0.06
     kin
    -0.06
    iblings
    -0.06
     meltdown
    -0.06
    Perform
    -0.06
    doctor
    -0.06
     meds
    -0.06
     virgin
    -0.06
    乐团
    -0.06
    POSITIVE LOGITS
    _SR
    0.08
    ="'.
    0.07
    ListItemIcon
    0.07
    的好处
    0.07
     onwards
    0.07
    ITA
    0.07
    ">';↵
    0.07
    ylim
    0.07
     resumed
    0.07
     быстро
    0.07
    Act Density 0.001%

    No Known Activations