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

    Neuronpedia

    INDEX
    Explanations

    Renaming places/things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Facebook
    -0.07
     transf
    -0.06
    863
    -0.06
    งค
    -0.06
    CDF
    -0.06
    包
    -0.06
     camps
    -0.06
     клі
    -0.06
     toprak
    -0.06
     explore
    -0.06
    POSITIVE LOGITS
    örü
    0.07
     glimps
    0.07
     aprove
    0.07
     Rencontres
    0.07
     Hawaiian
    0.07
    Throw
    0.06
     Ni
    0.06
    -urlencoded
    0.06
     InternalEnumerator
    0.06
    TestMethod
    0.06
    Act Density 0.052%

    No Known Activations