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

    Neuronpedia

    INDEX
    Explanations

    obstruct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cycle
    -0.07
    iele
    -0.07
    eden
    -0.06
     unordered
    -0.06
    든
    -0.06
     연
    -0.06
    (Equal
    -0.06
     인구
    -0.06
     ساعت
    -0.06
    노
    -0.06
    POSITIVE LOGITS
     obstruct
    0.07
    viron
    0.07
    sgiving
    0.07
     obchod
    0.07
    abr
    0.07
    854
    0.07
     MongoDB
    0.06
    shade
    0.06
     Wood
    0.06
    Dict
    0.06
    Act Density 0.005%

    No Known Activations