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
    Seriously
    -0.07
     maxx
    -0.07
     voiture
    -0.06
    Bullet
    -0.06
     Phone
    -0.06
    Inline
    -0.06
     روش
    -0.06
    Increase
    -0.06
     Bradley
    -0.06
    Ignore
    -0.06
    POSITIVE LOGITS
     COMMON
    0.07
    िच
    0.07
    χό
    0.07
    осудар
    0.06
    toBeDefined
    0.06
     collects
    0.06
    ัมพ
    0.06
     srov
    0.06
     coding
    0.06
     [("
    0.06
    Act Density 0.000%

    No Known Activations