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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Triangle
    -0.06
    чик
    -0.06
     bik
    -0.06
    ì
    -0.06
    dpi
    -0.06
     undercover
    -0.06
     vtx
    -0.06
     swims
    -0.05
    ih
    -0.05
     evacuate
    -0.05
    POSITIVE LOGITS
     ------
    0.07
     detailing
    0.07
    <Date
    0.07
    ................................................................
    0.07
    いや
    0.06
     MSI
    0.06
    .COLOR
    0.06
     XII
    0.06
     icons
    0.06
     techniques
    0.06
    Act Density 0.036%

    No Known Activations