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

    Neuronpedia

    INDEX
    Explanations

    mkdir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trailer
    -0.07
     downstream
    -0.06
     streaming
    -0.06
     Polit
    -0.06
    новаж
    -0.06
    抗
    -0.06
     confines
    -0.06
     Frankfurt
    -0.06
     Documentary
    -0.06
     sinus
    -0.06
    POSITIVE LOGITS
    род
    0.06
     LSM
    0.06
     keeps
    0.06
     disruptions
    0.06
    riendly
    0.06
    녕
    0.06
     SAFE
    0.06
     Arthropoda
    0.06
    .mkdirs
    0.06
    WriteBarrier
    0.06
    Act Density 0.004%

    No Known Activations